INDEX

Explanations

references to individuals in a possessive context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

cie

-0.15

dow

-0.14

orsche

-0.14

levant

-0.14

=context

-0.13

horizontal

-0.13

vas

-0.13

cou

-0.13

.metro

-0.13

 Jenkins

-0.13

POSITIVE LOGITS

/her

0.37

own

0.26

/she

0.23

panic

0.22

own

0.19

 prÃ³p

0.18

zelf

0.17

maal

0.16

editary

0.16

ewith

0.16

Activations Density 0.223%

references to individuals in a possessive context

No Comments

No Known Activations