INDEX

Explanations

references to personal ownership and relationships

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

aroo

-0.14

 rumours

-0.14

../../../

-0.13

itest

-0.13

ington

-0.13

asted

-0.13

xdb

-0.13

atti

-0.13

lite

-0.12

POSITIVE LOGITS

own

0.30

/her

0.21

zelf

0.21

SELF

0.20

self

0.19

 prÃ³p

0.19

Own

0.18

Own

0.17

 respective

0.17

rtle

0.17

Activations Density 0.997%

references to personal ownership and relationships

No Comments

No Known Activations