INDEX

Explanations

terms associated with health, risk, and statistical occurrence

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

SSIP

-0.15

anki

-0.15

noh

-0.15

 Madden

-0.14

Ð°Ð½Ð¸ÑĨ

-0.14

CAST

-0.14

irms

-0.13

amburg

-0.13

POSITIVE LOGITS

shan

0.16

 materia

0.14

ÑģÐµÐ½

0.14

aket

0.14

veis

0.14

Ð¾Ð´Ð°ÑĢ

0.14

placer

0.14

ä¸įå¾Ĺ

0.14

)did

0.13

tridges

0.13

Activations Density 0.035%

terms associated with health, risk, and statistical occurrence

No Comments

No Known Activations