INDEX

Explanations

mentions of boycotts and their contexts related to political or social issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ibling

-0.15

iller

-0.15

ochen

-0.15

 Ù¾Ø³Øª

-0.14

[strlen

-0.14

kola

-0.14

 entitlement

-0.14

ypad

-0.14

ØŃÙĩ

-0.14

inet

-0.14

POSITIVE LOGITS

Boy

0.50

 boycott

0.49

 boyc

0.41

div

0.35

Boy

0.34

BDS

0.33

boy

0.31

boy

0.29

 Ð±Ð¾Ð¹

0.26

Div

0.25

Activations Density 0.027%

mentions of boycotts and their contexts related to political or social issues

No Comments

No Known Activations