INDEX

Explanations

pronouns and verbs related to personal agency and character interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

raf

-0.16

probably

-0.16

hiro

-0.14

isku

-0.14

Ã¤nn

-0.14

 probably

-0.14

ListModel

-0.14

htar

-0.13

').'

-0.13

agra

-0.13

POSITIVE LOGITS

 ever

0.23

 varsa

0.21

à¹ĥà¸Ķ

0.19

fy

0.17

 anything

0.17

 tomorrow

0.17

fos

0.17

 hadn

0.17

 were

0.17

 somehow

0.17

Activations Density 0.278%

pronouns and verbs related to personal agency and character interactions

No Comments

No Known Activations