INDEX

Explanations

references to academic institutions and universities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

zb

-0.14

learner

-0.14

åĨĮ

-0.14

_mgr

-0.14

à¤¹à¤¨

-0.13

Ð¼Ð¸Ð½Ð¸ÑģÑĤÑĢÐ°

-0.13

âĢĮÚ¯Ø°

-0.13

Mgr

-0.13

__;

-0.12

{{{

-0.12

POSITIVE LOGITS

 School

0.36

's

0.35

’s

0.31

Law

0.29

 Libraries

0.28

 Department

0.28

 Medical

0.28

‘s

0.26

 Press

0.25

-aff

0.24

Activations Density 0.067%

references to academic institutions and universities

No Comments

No Known Activations