INDEX

Explanations

code that defines parameters and return values in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Ð°ÑĤÑĸ

-0.15

ç°

-0.14

ÃŃa

-0.14

Bounding

-0.14

atures

-0.14

 Wander

-0.14

ierre

-0.14

Ã³

-0.14

tam

-0.14

ature

-0.13

POSITIVE LOGITS

upal

0.16

Trad

0.16

poll

0.15

Occurred

0.15

bart

0.14

 Bare

0.14

empt

0.14

upert

0.14

isd

0.14

éīĦ

0.14

Activations Density 0.003%

code that defines parameters and return values in a programming context

No Comments

No Known Activations