INDEX

Explanations

themes related to media credibility and political discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

heimer

-0.15

rear

-0.14

 Ø³Ø¹

-0.14

awan

-0.14

£p

-0.14

HttpException

-0.13

Æ°á»Ŀng

-0.13

ToLocal

-0.13

.infinity

-0.13

Ø§Ø´Øª

-0.13

POSITIVE LOGITS

 objective

0.58

 neutral

0.56

 impartial

0.54

 unbiased

0.50

objective

0.49

 object

0.48

 neutrality

0.47

-object

0.47

-neutral

0.46

neutral

0.46

Activations Density 0.243%

themes related to media credibility and political discourse

No Comments

No Known Activations