INDEX

Explanations

nouns related to shops or places where goods are sold

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

uality

-0.19

ITU

-0.17

positions

-0.17

indi

-0.17

UAL

-0.17

itation

-0.16

ually

-0.16

ivated

-0.15

ousse

-0.15

ual

-0.15

POSITIVE LOGITS

ary

0.51

naire

0.41

aries

0.39

nement

0.36

naires

0.35

nel

0.33

ARY

0.31

er

0.29

ery

0.27

Ã¤re

0.27

Activations Density 0.097%

nouns related to shops or places where goods are sold

No Comments

No Known Activations