INDEX

Explanations

mentions of the letter 'U' or words that start with 'U'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Closing

-0.17

Ã¡m

-0.15

 closing

-0.15

cky

-0.14

ISA

-0.14

siz

-0.14

essa

-0.14

pad

-0.14

 Closing

-0.13

-pad

-0.13

POSITIVE LOGITS

imon

0.16

-runtime

0.15

semblies

0.15

stÃŃ

0.15

trecht

0.15

 dÃ¶nÃ¼ÅŁ

0.15

vais

0.15

ynamo

0.15

 REGARD

0.14

acht

0.14

Activations Density 0.026%

mentions of the letter 'U' or words that start with 'U'

No Comments

No Known Activations