INDEX

Explanations

references to factors in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

à¸±à¹Ī

-0.16

sor

-0.15

ucz

-0.15

 Audience

-0.14

ÎºÎ»Î·

-0.14

initWith

-0.14

ninger

-0.14

teg

-0.13

heimer

-0.13

 {{--<

-0.13

POSITIVE LOGITS

 ÙħØ«

0.15

unifu

0.15

(Void

0.15

azzo

0.14

vol

0.14

 Borg

0.14

spath

0.14

\Container

0.14

vol

0.14

ÑĢÐ¸Ð·

0.14

Activations Density 0.007%

references to factors in various contexts

No Comments

No Known Activations