INDEX

Explanations

terms associated with collaboration or partnerships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Related

-0.15

arella

-0.15

uges

-0.14

.related

-0.14

 Wright

-0.14

Sor

-0.14

DJ

-0.13

uggy

-0.13

sor

-0.13

POSITIVE LOGITS

.locals

0.20

ãĥ³ãĥĦ

0.17

-gnu

0.15

zew

0.14

wner

0.14

å¡

0.14

ajes

0.14

agan

0.14

UTIL

0.14

 maduras

0.14

Activations Density 0.359%

terms associated with collaboration or partnerships

No Comments

No Known Activations