INDEX

Explanations

lines that denote comments and 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 @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

eld

-0.14

ita

-0.14

ence

-0.14

unp

-0.13

cular

-0.13

cdb

-0.13

 aver

-0.13

mar

-0.13

 zast

-0.12

Unc

-0.12

POSITIVE LOGITS

ÅĽci

0.15

UGHT

0.14

 ëĭ

0.14

-io

0.14

ryfall

0.13

Å¡il

0.13

PERT

0.13

_digest

0.13

rift

0.13

Activations Density 0.082%

lines that denote comments and documentation in code

No Comments

No Known Activations