INDEX

Explanations

phrases indicating inquiry or seeking information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

achi

-0.17

.Proxy

-0.17

jÃł

-0.15

enu

-0.14

NET

-0.14

monds

-0.13

iei

-0.13

 voks

-0.13

 '\''

-0.13

inki

-0.13

POSITIVE LOGITS

 whether

0.20

uil

0.17

why

0.16

 about

0.16

whether

0.16

how

0.15

ENER

0.15

Î¸Î¹

0.14

.jdesktop

0.14

_about

0.14

Activations Density 0.048%

phrases indicating inquiry or seeking information

No Comments

No Known Activations