INDEX

Explanations

references to events and performances across various contexts

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

pragma

-0.17

lo

-0.15

ACKET

-0.14

IH

-0.14

rh

-0.14

 everywhere

-0.14

 Axel

-0.14

 Hybrid

-0.14

ur

-0.14

tec

-0.14

POSITIVE LOGITS

Pon

0.17

0.16

_redirected

0.15

 auss

0.14

 BigNumber

0.14

illard

0.14

vap

0.14

kÄ±

0.14

:variables

0.14

 BATCH

0.14

Activations Density 0.288%

references to events and performances across various contexts

No Comments

No Known Activations