INDEX

Explanations

the opening parentheses in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

engkap

-0.16

cona

-0.16

ibble

-0.15

.toolbox

-0.15

_OPENGL

-0.15

ampie

-0.14

.closePath

-0.14

kili

-0.14

atrice

-0.14

owo

-0.14

POSITIVE LOGITS

0.17

 epis

0.15

Ã©p

0.15

ÑĳÐ¼

0.15

 merg

0.15

ep

0.15

ichten

0.14

ad

0.14

 visual

0.14

Activations Density 0.155%

the opening parentheses in the text

No Comments

No Known Activations