INDEX

Explanations

phrases emphasizing necessity or assertions of identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 enter

-0.15

dyn

-0.15

Pou

-0.15

-0.14

Ð»Ð¸Ð½

-0.14

Mal

-0.14

tha

-0.13

 Danger

-0.13

 groove

-0.13

POSITIVE LOGITS

 pity

0.19

 pleasure

0.16

.scalablytyped

0.15

natural

0.15

nze

0.15

 true

0.15

Ã¤dchen

0.15

true

0.15

ixo

0.15

normal

0.15

Activations Density 0.126%

phrases emphasizing necessity or assertions of identity

No Comments

No Known Activations