INDEX

Explanations

references to media influence and coverage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

tol

-0.14

à¹ĥà¸Ī

-0.14

lotte

-0.14

emoc

-0.14

 secre

-0.14

 DISCLAIMER

-0.14

idar

-0.14

 çŃĶ

-0.13

arged

-0.13

å»³

-0.13

POSITIVE LOGITS

 coverage

0.47

coverage

0.40

 Coverage

0.38

 reporting

0.37

Coverage

0.35

 media

0.34

 headlines

0.34

æĬ¥éģĵ

0.30

 Reporting

0.30

 news

0.29

Activations Density 0.163%

references to media influence and coverage

No Comments

No Known Activations

references to media influence and coverage

No Comments

No Known Activations