INDEX

Explanations

programming syntax elements and structure within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

bip

-0.17

unker

-0.15

orie

-0.14

/column

-0.14

ãģĵãģĿ

-0.14

ãĥ¯ãĤ¤ãĥĪ

-0.14

ÑĤÐµÐ½

-0.14

Deg

-0.13

ols

-0.13

IfExists

-0.13

POSITIVE LOGITS

indre

0.17

 //{↵

0.15

missive

0.14

.bit

0.14

sig

0.14

Ã¡st

0.14

mia

0.14

Ð¾Ð´Ð°

0.13

çħ§

0.13

//

0.13

Activations Density 0.078%

programming syntax elements and structure within code

No Comments

No Known Activations