INDEX

Explanations

words that describe the effects on individuals or groups, particularly regarding health or well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

oger

-0.14

_defs

-0.14

 MainAxisAlignment

-0.13

 kriz

-0.13

resher

-0.13

adin

-0.13

 cres

-0.13

otic

-0.13

jd

-0.13

ĺ

-0.13

POSITIVE LOGITS

Ð»Ð¾Ð¶

0.16

ably

0.16

Ð»Ð°Ð³

0.15

 Hath

0.14

asca

0.14

adh

0.13

 understanding

0.13

£½

0.13

 ment

0.13

Activations Density 0.090%

words that describe the effects on individuals or groups, particularly regarding health or well-being

No Comments

No Known Activations