INDEX

Explanations

phrases that highlight the significance and impact of various subjects or themes in a nuanced manner

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

uke

-0.16

 kidding

-0.14

 humanities

-0.14

 laisse

-0.14

rellas

-0.13

 however

-0.13

powered

-0.13

Ä±lan

-0.13

è¥

-0.13

ÑĨÐµÐ¹

-0.13

POSITIVE LOGITS

imes

0.15

 CONTRIBUTORS

0.15

vt

0.15

hab

0.15

uhl

0.14

dol

0.14

idon

0.14

uther

0.14

cak

0.14

edia

0.14

Activations Density 0.712%

phrases that highlight the significance and impact of various subjects or themes in a nuanced manner

No Comments

No Known Activations