INDEX

Explanations

prepositions and expressions of direction or movement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 somewhere

-0.16

 none

-0.15

 humans

-0.15

none

-0.15

 None

-0.15

sez

-0.14

oir

-0.14

.none

-0.14

Ī¬

-0.14

quet

-0.13

POSITIVE LOGITS

 everything

0.71

everything

0.60

 Everything

0.56

Everything

0.54

ä¸ĢåĪĩ

0.46

 every

0.45

 tudo

0.45

 EVERY

0.40

 everyone

0.40

 alles

0.39

Activations Density 0.042%

prepositions and expressions of direction or movement

No Comments

No Known Activations