INDEX

Explanations

specific grammatical endings and markers used in different contexts

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

ninger

-0.17

onden

-0.16

bung

-0.15

taire

-0.15

ë¹Į

-0.15

 Balt

-0.15

DEC

-0.15

 mÃ³

-0.14

fir

-0.14

 handleMessage

-0.14

POSITIVE LOGITS

leton

0.15

yte

0.15

ãĥ³ãĥķ

0.15

 Heights

0.15

 Horton

0.15

 Orth

0.14

ione

0.14

iales

0.14

 grass

0.14

ickers

0.14

Activations Density 0.341%

specific grammatical endings and markers used in different contexts

No Comments

No Known Activations