INDEX

Explanations

references to quantities, specifically measurements or values in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 latter

-0.20

-0.18

in

-0.18

tom

-0.18

dust

-0.17

mÃ¡

-0.15

Ùħ

-0.14

tÃ©

-0.14

-0.13

POSITIVE LOGITS

azen

0.15

raries

0.15

ãĥ¼ãĥĵ

0.15

(...)↵

0.15

AUDIO

0.15

greSQL

0.14

StackSize

0.14

utor

0.14

 tieten

0.13

ErrorException

0.13

Activations Density 0.028%

references to quantities, specifically measurements or values in various contexts

No Comments

No Known Activations