INDEX

Explanations

connections and references to relationships or associations in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

-0.16

ypo

-0.16

ÃŃrk

-0.16

alley

-0.15

vit

-0.15

KeyType

-0.14

ebin

-0.14

vsp

-0.14

ustin

-0.14

usr

-0.13

POSITIVE LOGITS

oho

0.17

olina

0.14

zb

0.14

à¸¹à¸£

0.14

Äı

0.14

ainter

0.14

 Water

0.14

kate

0.14

Î¿ÏħÏģÎ³

0.14

uf

0.14

Activations Density 0.005%

connections and references to relationships or associations in data

No Comments

No Known Activations