INDEX

Explanations

references to headwear and related clothing items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

yte

-0.15

arda

-0.15

 bufsize

-0.14

MOVED

-0.14

oku

-0.13

inia

-0.13

enia

-0.13

Î¹

-0.13

ydk

-0.13

ayout

-0.13

POSITIVE LOGITS

hat

0.47

 hats

0.44

Hat

0.38

hat

0.37

å¸½

0.37

 Hats

0.35

Hat

0.34

 caps

0.32

_hat

0.30

 straw

0.30

Activations Density 0.035%

references to headwear and related clothing items

No Comments

No Known Activations