INDEX

Explanations

phrases indicating personal reflections or feelings about experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

auen

-0.15

tÃ¼

-0.14

veis

-0.14

Î³Î¿Ïħ

-0.14

apiro

-0.14

ylland

-0.14

ious

-0.13

ruba

-0.13

tx

-0.13

mÃ®

-0.13

POSITIVE LOGITS

us

0.22

 many

0.20

him

0.15

us

0.15

many

0.15

Ð¼ÐµÑĩ

0.15

asm

0.15

eyer

0.15

arga

0.15

ActionCreators

0.15

Activations Density 0.105%

phrases indicating personal reflections or feelings about experiences

No Comments

No Known Activations