INDEX

Explanations

references to Twitter

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

iaz

-0.18

''"

-0.16

 eldre

-0.15

edula

-0.14

atab

-0.14

 Katz

-0.14

ickey

-0.14

Ø¨ÙĪØ§Ø³Ø·Ø©

-0.14

licer

-0.14

atalog

-0.14

POSITIVE LOGITS

 prec

0.16

wind

0.16

æĩ

0.15

Ä±rak

0.14

DC

0.14

avin

0.14

CHA

0.13

loat

0.13

ment

0.13

RMS

0.13

Activations Density 0.001%

references to Twitter

No Comments

No Known Activations