INDEX

Explanations

expressions of moral judgement and correctness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

adel

-0.17

à¤Ī

-0.17

alles

-0.15

ç³

-0.15

rey

-0.15

Ø¡

-0.15

incinn

-0.15

aeda

-0.15

cter

-0.14

POSITIVE LOGITS

Cla

0.15

icha

0.15

 createAction

0.15

ima

0.15

TZ

0.14

cha

0.14

Ð¾Ð¶Ð´

0.14

.Paint

0.14

ero

0.14

uset

0.14

Activations Density 0.073%

expressions of moral judgement and correctness

No Comments

No Known Activations