INDEX

Explanations

components of structured data or content organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

loo

-0.18

rella

-0.17

Dud

-0.17

ÄĽn

-0.17

iese

-0.17

nila

-0.14

Moo

-0.14

ÐµÐ³Ð¾Ð´

-0.14

etti

-0.14

antee

-0.14

POSITIVE LOGITS

coma

0.16

ares

0.14

iglia

0.14

ENSE

0.14

dem

0.14

 Hermes

0.13

istrator

0.13

ushima

0.13

rok

0.13

Activations Density 0.068%

components of structured data or content organization

No Comments

No Known Activations