INDEX

Explanations

numeric values and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

bal

-0.17

 compens

-0.17

rab

-0.16

yny

-0.16

 organ

-0.16

mar

-0.15

soc

-0.15

ob

-0.15

 ages

-0.15

PIC

-0.15

POSITIVE LOGITS

ÑĻ

0.18

ibar

0.17

uci

0.17

 OnTrigger

0.16

eca

0.16

ĺ

0.16

ãĢģãĢģ

0.15

(strict

0.15

KeyName

0.15

ekim

0.15

Activations Density 0.007%

numeric values and measurements

No Comments

No Known Activations