INDEX

Explanations

questions indicating a need for information or assistance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

vell

-0.15

zt

-0.14

zel

-0.13

lik

-0.13

leanup

-0.13

ÑĢÐ¾Ñĩ

-0.13

ÅĻit

-0.13

uld

-0.13

amt

-0.13

oko

-0.13

POSITIVE LOGITS

yat

0.17

 Sham

0.16

eken

0.15

yw

0.15

-plugins

0.15

Marshal

0.14

éļ

0.14

 sham

0.13

esModule

0.13

lan

0.13

Activations Density 0.016%

questions indicating a need for information or assistance

No Comments

No Known Activations

questions indicating a need for information or assistance

No Comments

No Known Activations