INDEX

Explanations

references to parts or sections within a series or document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

achts

-0.17

ÅŁa

-0.14

visa

-0.13

resco

-0.13

kat

-0.13

 bindActionCreators

-0.13

AUSE

-0.13

 fres

-0.13

ÄŁa

-0.13

POSITIVE LOGITS

ents

0.16

atz

0.15

 manners

0.15

ey

0.14

uci

0.14

agree

0.14

rosso

0.14

_salt

0.14

 salt

0.14

arov

0.14

Activations Density 0.034%

references to parts or sections within a series or document

No Comments

No Known Activations