INDEX

Explanations

phrases indicating ownership or possession

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

plex

-0.15

ams

-0.15

ago

-0.15

agos

-0.15

 Eisen

-0.14

.library

-0.14

_ADAPTER

-0.14

å¾®è½¯éĽħé»ĳ

-0.14

å²³

-0.14

ONTAL

-0.13

POSITIVE LOGITS

 seperate

0.22

 Separate

0.22

 separate

0.21

own

0.17

omanip

0.15

parate

0.15

 dedicated

0.15

 Ð¾ÑĤÐ´ÐµÐ»ÑĮ

0.15

ondere

0.15

Activations Density 0.009%

phrases indicating ownership or possession

No Comments

No Known Activations