INDEX

Explanations

terms related to politics and political commentary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

encil

-0.16

ITOR

-0.16

Î¹Î±Îº

-0.16

anova

-0.14

entials

-0.14

 Vinci

-0.14

ego

-0.14

legg

-0.14

.sym

-0.14

ANCE

-0.14

POSITIVE LOGITS

ische

0.36

ischen

0.32

isch

0.32

ischer

0.32

isches

0.30

ches

0.21

ishes

0.19

ickÃ©

0.19

ycz

0.19

iker

0.18

Activations Density 0.043%

terms related to politics and political commentary

No Comments

No Known Activations