INDEX

Explanations

references to authors and academic citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

apesh

-0.14

Î³Î¿

-0.14

Äįan

-0.14

apur

-0.13

arine

-0.13

orgia

-0.13

lamak

-0.13

 âľĵ

-0.13

ìļ°

-0.13

 forensic

-0.13

POSITIVE LOGITS

0.21

0.20

0.19

 Laugh

0.18

0.16

 independently

0.16

ulis

0.16

 USSR

0.16

 Lands

0.15

affle

0.15

Activations Density 0.161%

references to authors and academic citations

No Comments

No Known Activations