INDEX

Explanations

concepts and terms related to principles or guidelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ÙĪØ·

-0.18

gie

-0.18

reat

-0.16

elian

-0.16

akan

-0.16

ney

-0.15

eat

-0.15

arrant

-0.15

 Airways

-0.14

quisition

-0.14

POSITIVE LOGITS

-agent

0.31

ities

0.25

 investigator

0.23

ps

0.21

 Investig

0.21

/pr

0.20

-Agent

0.20

pal

0.19

stown

0.18

 investigators

0.18

Activations Density 0.019%

concepts and terms related to principles or guidelines

No Comments

No Known Activations