INDEX

Explanations

descriptive language related to experiences in nature and leisure activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ucci

-0.16

chaft

-0.15

tings

-0.15

oretical

-0.15

ãģĵãģĿ

-0.15

hasOne

-0.14

tle

-0.14

/octet

-0.14

'Ä±n

-0.14

Åĳ

-0.14

POSITIVE LOGITS

ìį¨

0.20

theast

0.18

sett

0.17

 behalf

0.17

posit

0.17

yssey

0.17

ÑģÑıÐ³

0.16

readcr

0.15

è®¸

0.15

Ĭ

0.15

Activations Density 4.049%

descriptive language related to experiences in nature and leisure activities

No Comments

No Known Activations