INDEX

Explanations

blocks of comments or documentation 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 @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

avigator

-0.16

 desert

-0.15

nbsp

-0.15

ump

-0.15

aston

-0.15

 Jain

-0.15

 Desert

-0.14

igi

-0.14

ider

-0.14

rs

-0.14

POSITIVE LOGITS

ÅĻet

0.19

 AssemblyCopyright

0.16

ycz

0.16

phis

0.16

Tester

0.15

ãĥ«ãĥķ

0.15

/Dk

0.15

ichert

0.15

icaret

0.15

Touches

0.14

Activations Density 0.004%

blocks of comments or documentation in code

No Comments

No Known Activations