INDEX

Explanations

references to hats and headwear

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 clothes

-0.16

Hou

-0.15

endon

-0.15

 Clothes

-0.15

 dresses

-0.15

 Clothing

-0.14

_skin

-0.14

 Hund

-0.14

 skin

-0.14

hyp

-0.14

POSITIVE LOGITS

hat

0.76

 hats

0.69

Hat

0.67

hat

0.62

Hat

0.60

å¸½

0.59

 Hats

0.55

_hat

0.49

cap

0.49

 caps

0.45

Activations Density 0.138%

references to hats and headwear

No Comments

No Known Activations