INDEX

Explanations

references to legislative districts and redistricting processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uml

-0.17

anst

-0.17

icha

-0.16

neau

-0.15

ì°¨

-0.15

é«

-0.15

hek

-0.15

steder

-0.15

ÑĢÑıÐ´Ñĥ

-0.15

ë£Į

-0.15

POSITIVE LOGITS

 boundaries

0.27

 boundary

0.24

istrict

0.23

 Boundary

0.21

boundary

0.21

 maps

0.20

 reap

0.19

Boundary

0.19

 redraw

0.19

 redistrib

0.19

Activations Density 0.030%

references to legislative districts and redistricting processes

No Comments

No Known Activations