INDEX

Explanations

phrases indicating location or access in a spatial context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 subclass

-0.15

dup

-0.14

 sphere

-0.14

_subtitle

-0.14

 subtype

-0.14

 lá»ĩ

-0.13

_votes

-0.13

ostel

-0.13

subtitle

-0.13

queries

-0.13

POSITIVE LOGITS

 spots

0.46

 places

0.43

 locations

0.42

 strategic

0.38

 areas

0.35

 points

0.35

 parts

0.32

 Locations

0.30

 spot

0.30

Places

0.30

Activations Density 0.110%

phrases indicating location or access in a spatial context

No Comments

No Known Activations