INDEX

Explanations

non-standard formatting and characters in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

eren

-0.17

cka

-0.17

itta

-0.15

ickle

-0.15

hind

-0.15

orf

-0.15

Pla

-0.14

erten

-0.14

etting

-0.14

usercontent

-0.14

POSITIVE LOGITS

utton

0.18

 Exped

0.17

ungan

0.17

oti

0.17

ipse

0.16

 Òĳ

0.15

eatures

0.15

iÐ²

0.14

AMED

0.14

/goto

0.14

Activations Density 0.002%

non-standard formatting and characters in the text

No Comments

No Known Activations