INDEX

Explanations

references to films, television, and their creators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Funk

-0.16

imeline

-0.16

Î»Î±

-0.15

avid

-0.14

enge

-0.14

 Valor

-0.14

 Surround

-0.13

ÏĦÎµ

-0.13

ixel

-0.13

 chore

-0.13

POSITIVE LOGITS

 Sund

0.24

SX

0.21

SX

0.21

 indie

0.20

 TIFF

0.18

 Indie

0.18

 Independent

0.18

 Criterion

0.18

RuntimeException

0.17

 independent

0.17

Activations Density 0.118%

references to films, television, and their creators

No Comments

No Known Activations

references to films, television, and their creators

No Comments

No Known Activations