INDEX

Explanations

elements related to metadata or documentation in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ramer

-0.17

entre

-0.15

 borderBottom

-0.15

.deep

-0.15

utton

-0.15

eing

-0.14

 impulse

-0.14

_den

-0.14

rement

-0.14

alary

-0.14

POSITIVE LOGITS

fried

0.16

licht

0.16

ByExample

0.15

PUTE

0.15

Č

0.14

heat

0.14

 Cair

0.14

setDisplay

0.13

Ĥæķ°

0.13

<<<<<<<

0.13

Activations Density 0.003%

elements related to metadata or documentation in code

No Comments

No Known Activations