INDEX

Explanations

phrases indicating quantity or amount

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ãģ¡ãĤĩ

-0.14

owers

-0.14

/Dk

-0.14

clair

-0.14

ernen

-0.13

*.

-0.13

@student

-0.13

 gratuites

-0.13

upro

-0.13

 handful

-0.13

POSITIVE LOGITS

 similar

0.23

similar

0.21

 enough

0.20

 same

0.18

same

0.17

ë³´ëĭ¤

0.16

 sufficiently

0.16

 benzer

0.15

suf

0.15

 quite

0.15

Activations Density 0.070%

phrases indicating quantity or amount

No Comments

No Known Activations