INDEX

Explanations

instances of the word "huge"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ries

-0.15

iant

-0.14

ekil

-0.13

cht

-0.13

 gris

-0.13

isans

-0.13

ulfilled

-0.13

ih

-0.13

inker

-0.13

 haze

-0.13

POSITIVE LOGITS

lage

0.15

erne

0.14

redient

0.14

CLA

0.14

icone

0.14

-scale

0.13

 Shoes

0.13

ãĤ¤ãĤ¹

0.13

Ø¨Ø§Øª

0.13

 Foods

0.13

Activations Density 0.008%

instances of the word "huge"

No Comments

No Known Activations