INDEX

Explanations

specific names or terms with 'ra' in them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

beck

-0.17

iron

-0.17

rops

-0.16

dling

-0.16

zap

-0.15

apus

-0.15

¥

-0.15

rios

-0.14

rons

-0.14

 Canton

-0.14

POSITIVE LOGITS

0.24

eel

0.20

ffic

0.19

fi

0.19

eus

0.18

ë§Īëĭ¤

0.17

eck

0.17

jp

0.17

ford

0.17

Activations Density 0.051%

specific names or terms with 'ra' in them

No Comments

No Known Activations