INDEX

Explanations

programming-related constructs and return statements 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 @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

uman

-0.15

 à¤°à¤¸

-0.15

Ãª

-0.15

%H

-0.14

ulty

-0.14

 YYSTYPE

-0.14

igham

-0.14

emark

-0.14

RLF

-0.14

emes

-0.13

POSITIVE LOGITS

unsch

0.17

 Darkness

0.17

emsp

0.16

iyat

0.15

asca

0.15

quia

0.14

.Enqueue

0.14

holm

0.14

oley

0.14

Lew

0.13

Activations Density 0.003%

programming-related constructs and return statements in code

No Comments

No Known Activations