INDEX

Explanations

possessive pronouns and references to ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 possibility

-0.14

atti

-0.14

onical

-0.13

loquent

-0.13

 brink

-0.12

ises

-0.12

 thing

-0.12

Sibling

-0.12

igure

-0.12

POSITIVE LOGITS

own

0.31

/her

0.23

zelf

0.22

self

0.21

 prÃ³p

0.21

rtle

0.21

SELF

0.19

_own

0.19

Own

0.18

Own

0.18

Activations Density 0.991%

possessive pronouns and references to ownership

No Comments

No Known Activations