INDEX

Explanations

instances of the word "closed" or related terms discussing closure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

jak

-0.16

oin

-0.16

fork

-0.14

 Pierce

-0.14

athed

-0.14

oen

-0.14

sha

-0.14

atrix

-0.13

POSITIVE LOGITS

-caption

0.28

/open

0.27

 closed

0.25

 Closed

0.25

éĸī

0.24

closed

0.24

éĹŃ

0.24

-loop

0.23

Closed

0.23

-door

0.21

Activations Density 0.038%

instances of the word "closed" or related terms discussing closure

No Comments

No Known Activations