INDEX

Explanations

references to social and political conflict, including terms relating to discrimination and opposition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

amage

-0.17

ullo

-0.16

Ð²Ð°Ð´

-0.16

-0.15

pector

-0.15

pcm

-0.15

utsch

-0.15

utt

-0.14

rai

-0.14

pus

-0.14

POSITIVE LOGITS

 perceived

0.18

ÑĢÑĥÑģ

0.15

DEL

0.14

 poor

0.14

Hog

0.14

ãģ¹ãģį

0.14

ldata

0.14

iki

0.13

ares

0.13

Wag

0.13

Activations Density 0.217%

references to social and political conflict, including terms relating to discrimination and opposition

No Comments

No Known Activations