INDEX

Explanations

phrases indicating understanding or familiarity with a subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ingen

-0.16

unker

-0.15

andum

-0.15

ÑıÑĩ

-0.14

Ã¡Å¡

-0.14

.bool

-0.14

ÙĤÙĬ

-0.13

Verification

-0.13

éħ

-0.13

lix

-0.13

POSITIVE LOGITS

 understanding

0.50

 know

0.50

 knowledge

0.49

 knows

0.48

 understand

0.48

 understands

0.48

çŁ¥éģĵ

0.42

 knowing

0.42

 knew

0.42

 KNOW

0.41

Activations Density 0.425%

phrases indicating understanding or familiarity with a subject

No Comments

No Known Activations