INDEX

Explanations

programming constructs and keywords used in code, particularly related to configuration, types, and functions

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

sav

-0.22

 progressive

-0.19

Sav

-0.19

 forward

-0.18

-s

-0.18

sav

-0.17

enity

-0.17

forward

-0.16

Ã¼h

-0.15

POSITIVE LOGITS

 altern

0.15

izoph

0.14

Gim

0.14

tail

0.14

Äįek

0.14

Ry

0.14

chai

0.13

swick

0.13

-eslint

0.13

gos

0.13

Activations Density 0.214%

programming constructs and keywords used in code, particularly related to configuration, types, and functions

No Comments

No Known Activations