INDEX

Explanations

references to auditory perception or experiences involving listening

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

hread

-0.18

å§¿

-0.17

gor

-0.15

 scene

-0.15

owa

-0.15

chin

-0.14

tems

-0.14

ced

-0.14

"text

-0.14

POSITIVE LOGITS

kening

0.23

/read

0.18

ald

0.18

/sm

0.17

 about

0.17

wig

0.16

/watch

0.16

/view

0.15

_about

0.15

isay

0.15

Activations Density 0.026%

references to auditory perception or experiences involving listening

No Comments

No Known Activations