INDEX

Explanations

code-related components and functions in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

-0.15

ART

-0.15

 Bart

-0.14

REET

-0.14

urer

-0.14

.assertThat

-0.14

angl

-0.14

 Floyd

-0.14

POSITIVE LOGITS

 Drive

0.20

Drive

0.19

-drive

0.18

 drive

0.16

shelf

0.16

#ac

0.15

ãĤ

0.15

 PATCH

0.15

drive

0.15

 DRIVE

0.15

Activations Density 0.010%

code-related components and functions in programming

No Comments

No Known Activations