INDEX

Explanations

phrases related to political controversy and accusations

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

 Diseases

-0.16

 diseases

-0.15

 Impl

-0.15

sez

-0.14

 wars

-0.14

 Fires

-0.14

ammable

-0.13

Bom

-0.13

launcher

-0.13

à¸§à¸ģ

-0.13

POSITIVE LOGITS

 incident

0.60

 event

0.50

 episode

0.47

incident

0.44

 Incident

0.39

 encounter

0.38

äºĭä»¶

0.37

 events

0.36

 experience

0.35

episode

0.35

Activations Density 0.280%

phrases related to political controversy and accusations

No Comments

No Known Activations