INDEX

Explanations

dates and access information

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

icast

-0.17

outil

-0.15

adam

-0.15

htub

-0.14

 Bolton

-0.14

 Mime

-0.14

emat

-0.14

imet

-0.14

@[

-0.14

POSITIVE LOGITS

.toLocale

0.15

incl

0.15

 Ãºn

0.15

*sizeof

0.15

éĻµ

0.14

itulo

0.14

shal

0.14

bd

0.13

adier

0.13

ëł

0.13

Activations Density 0.018%

dates and access information

No Comments

No Known Activations