INDEX

Explanations

concepts related to interaction and relationships, particularly in physical and abstract contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ODEV

-0.16

kovÄĽ

-0.15

TOTYPE

-0.15

 ØµÙĦÙī

-0.15

_Tick

-0.15

YRO

-0.15

_FOREACH

-0.15

ç±

-0.14

.HOUR

-0.14

nth

-0.14

POSITIVE LOGITS

 interaction

0.45

 interactions

0.40

 collision

0.38

interaction

0.37

 collisions

0.35

 Interaction

0.35

 interact

0.34

 encounter

0.34

collision

0.34

 interacts

0.33

Activations Density 0.176%

concepts related to interaction and relationships, particularly in physical and abstract contexts

No Comments

No Known Activations