INDEX

Explanations

occurrences of programming syntax and comments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

zelf

-0.15

-0.14

esh

-0.14

alink

-0.14

icter

-0.14

'll

-0.14

ÐµÐ¼Ð¾

-0.13

't

-0.13

Ã´n

-0.13

POSITIVE LOGITS

VI

0.16

 endregion

0.14

 TODO

0.14

owell

0.14

iton

0.13

ê·ł

0.13

 %%↵

0.13

TODO

0.13

Activations Density 0.012%

occurrences of programming syntax and comments

No Comments

No Known Activations