INDEX

Explanations

names of people and potentially some brands or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Pit

-0.16

.struct

-0.15

@Spring

-0.14

DUCT

-0.14

 DependencyProperty

-0.14

 Trib

-0.14

winner

-0.14

 láº«n

-0.14

hoff

-0.14

rix

-0.14

POSITIVE LOGITS

chal

0.17

icht

0.17

fraction

0.16

andler

0.15

 ëıĻ

0.15

rafted

0.14

PropTypes

0.14

ocale

0.14

afen

0.14

Activations Density 0.398%

names of people and potentially some brands or organizations

No Comments

No Known Activations