INDEX

Explanations

function return statements in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

amburg

-0.15

odega

-0.15

entials

-0.15

ÄĽÅ¾

-0.15

xo

-0.15

icros

-0.15

wner

-0.15

coder

-0.14

omik

-0.14

ÄĽk

-0.14

POSITIVE LOGITS

 Fior

0.20

 otherwise

0.16

AME

0.15

pac

0.14

 Barton

0.14

ies

0.13

 Chapel

0.13

ãĥ¬ãĤ¤

0.13

.lu

0.13

Î±Î»

0.13

Activations Density 0.029%

function return statements in a programming context

No Comments

No Known Activations