INDEX

Explanations

references to software development processes and versioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

íķĺìļ°

-0.15

èĥŀ

-0.15

reo

-0.14

 ÑŁ

-0.14

Clip

-0.14

/desktop

-0.14

ennon

-0.14

ëľ

-0.14

è¦

-0.14

ROTO

-0.14

POSITIVE LOGITS

 branch

0.26

 branches

0.23

branch

0.21

Branch

0.21

PR

0.20

 Branch

0.20

branches

0.20

.branch

0.20

 code

0.19

 commit

0.19

Activations Density 0.116%

references to software development processes and versioning

No Comments

No Known Activations