INDEX

Explanations

references to people, places, or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

idor

-0.15

insic

-0.14

olls

-0.14

/welcome

-0.14

ookie

-0.14

èĢ

-0.13

eus

-0.13

sumer

-0.13

 possibilit

-0.13

cade

-0.13

POSITIVE LOGITS

asca

0.17

kiye

0.14

 OnTrigger

0.14

idis

0.14

 Guns

0.14

 ucwords

0.13

rem

0.13

OffsetTable

0.13

Ø§ÙĬØ±

0.13

SError

0.13

Activations Density 0.252%

references to people, places, or entities

No Comments

No Known Activations