INDEX

Explanations

technical and file-related terms commonly associated with software documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

åĲ¹

-0.16

oby

-0.15

 Hath

-0.14

getattr

-0.14

aÅ¼

-0.14

Dit

-0.14

irut

-0.14

Ð°Ð±Ð¾

-0.14

Pane

-0.13

ÏĩÏģÎ¹

-0.13

POSITIVE LOGITS

Wyn

0.15

rette

0.14

icons

0.14

 kontro

0.14

kin

0.14

 æ¥Ń

0.14

.initializeApp

0.14

ur

0.14

ainted

0.14

unta

0.14

Activations Density 0.009%

technical and file-related terms commonly associated with software documentation

No Comments

No Known Activations