INDEX

Explanations

references to variables in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

TING

-0.17

ea

-0.16

ra

-0.15

elines

-0.15

ILITY

-0.15

eds

-0.15

ka

-0.14

berman

-0.14

eso

-0.14

mund

-0.14

POSITIVE LOGITS

mente

0.17

ncia

0.16

spath

0.15

culate

0.15

stown

0.15

+offset

0.15

ization

0.15

agate

0.15

Ð¾ÑĩÐ½Ð¾

0.14

ignum

0.14

Activations Density 0.032%

references to variables in programming contexts

No Comments

No Known Activations