INDEX

Explanations

mathematical notations and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

phinx

-0.18

ainment

-0.14

evice

-0.14

JKLM

-0.14

tingham

-0.14

 Fate

-0.14

wares

-0.14

ÙģÙĬ

-0.13

/filepath

-0.13

ToFront

-0.13

POSITIVE LOGITS

 Lantern

0.17

atham

0.17

($)

0.15

æŁĵ

0.15

Es

0.15

-pic

0.15

 privat

0.15

ecer

0.14

obs

0.14

ucci

0.13

Activations Density 0.311%

mathematical notations and symbols

No Comments

No Known Activations