INDEX

Explanations

special comments or directives typically used in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

othy

-0.16

Åĳs

-0.15

aneous

-0.14

Eh

-0.14

/at

-0.14

à¤¾à¤¨à¤¨

-0.14

 Atlas

-0.14

ual

-0.14

Ð¶Ñĥ

-0.14

ograd

-0.13

POSITIVE LOGITS

ippo

0.14

readcr

0.14

iferay

0.14

ÐºÐ°ÑĤ

0.14

icer

0.14

 perms

0.14

ampo

0.14

acey

0.14

ingle

0.13

ardy

0.13

Activations Density 0.004%

special comments or directives typically used in programming

No Comments

No Known Activations