INDEX

Explanations

expressions of belief or speculation regarding events or statements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ussen

-0.15

Ãºt

-0.15

 partic

-0.15

pee

-0.15

erie

-0.14

ÑĢÐµÑĤÑĮ

-0.14

ointment

-0.14

stoff

-0.14

eting

-0.14

imary

-0.14

POSITIVE LOGITS

 TCHAR

0.16

äºİ

0.15

ly

0.15

ed

0.14

sole

0.14

ruk

0.14

ONSE

0.14

0.13

 Richards

0.13

Activations Density 0.093%

expressions of belief or speculation regarding events or statements

No Comments

No Known Activations