INDEX

Explanations

references to people associated with the initials "ML"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

elle

-0.18

ES

-0.17

EH

-0.16

oes

-0.16

els

-0.15

 Gabriel

-0.15

htag

-0.15

es

-0.15

ine

-0.14

etr

-0.14

POSITIVE LOGITS

ambda

0.22

0.20

TI

0.20

ateral

0.19

ounge

0.19

0.18

erate

0.18

abeled

0.18

earning

0.18

Activations Density 0.037%

references to people associated with the initials "ML"

No Comments

No Known Activations