INDEX

Explanations

mentions of political figures and discussions related to political activities

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

.nih

-0.16

 ìĿ¸êµ¬

-0.15

anness

-0.15

amber

-0.14

bjerg

-0.14

RIX

-0.14

Ã¤Ã¤n

-0.14

ÑĢÐ°Ð¿

-0.14

rix

-0.13

alach

-0.13

POSITIVE LOGITS

 activists

0.33

 activist

0.31

activ

0.30

 radical

0.30

 radicals

0.29

 anti

0.29

 activism

0.28

 aktiv

0.28

 political

0.28

 Activ

0.28

Activations Density 0.294%

mentions of political figures and discussions related to political activities

No Comments

No Known Activations