INDEX

Explanations

questions and requests for information or engagement from the audience

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

lass

-0.16

Ã©ri

-0.15

steen

-0.15

pez

-0.14

inger

-0.14

 lump

-0.14

 Campbell

-0.13

earn

-0.13

Variables

-0.13

POSITIVE LOGITS

urum

0.17

ToWorld

0.16

 rÃºt

0.15

kaar

0.15

æ°ĹæĮģãģ¡

0.14

.opend

0.14

ìłĿ

0.14

Äįet

0.14

commend

0.14

glob

0.14

Activations Density 0.049%

questions and requests for information or engagement from the audience

No Comments

No Known Activations