INDEX

Explanations

phrases indicating inclusion or connection between multiple subjects or ideas

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

ÑĥÐ»Ñİ

-0.16

BOVE

-0.16

anson

-0.15

ZW

-0.15

amoto

-0.15

 METH

-0.15

iro

-0.14

agged

-0.14

amo

-0.14

uw

-0.14

POSITIVE LOGITS

 Rubin

0.15

rq

0.14

rophe

0.14

 cogn

0.14

mma

0.14

piel

0.13

cad

0.13

 Draw

0.13

.locale

0.13

 nutzen

0.13

Activations Density 0.009%

phrases indicating inclusion or connection between multiple subjects or ideas

No Comments

No Known Activations