INDEX

Explanations

instances of dialogue and spoken interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

akedown

-0.14

eyen

-0.13

 BÃ¶l

-0.13

neÄŁi

-0.13

opian

-0.13

Sez

-0.13

Rag

-0.12

 ÐłÐ°Ñģ

-0.12

Ã¤lt

-0.12

encing

-0.12

POSITIVE LOGITS

xr

0.26

iar

0.26

lr

0.26

lar

0.25

jr

0.24

yar

0.24

qr

0.23

yre

0.23

ierz

0.23

xr

0.23

Activations Density 0.261%

instances of dialogue and spoken interactions

No Comments

No Known Activations