INDEX

Explanations

terms related to political ideologies, specifically distinguishing between liberal and conservative viewpoints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

lasses

-0.15

kin

-0.14

hsi

-0.14

tweet

-0.14

ollar

-0.14

itra

-0.14

hal

-0.14

uci

-0.14

jÃŃm

-0.13

ç´¯

-0.13

POSITIVE LOGITS

unker

0.17

-Christian

0.15

ograd

0.15

-leaning

0.15

/lib

0.15

/social

0.15

 credentials

0.14

zac

0.14

/mod

0.14

 veget

0.14

Activations Density 0.029%

terms related to political ideologies, specifically distinguishing between liberal and conservative viewpoints

No Comments

No Known Activations