INDEX

Explanations

references to programming languages and associated libraries

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

-0.16

 Depth

-0.15

Depth

-0.15

Ð¸ÑģÑĤÑĢÐ°

-0.15

TOTYPE

-0.14

 Claus

-0.13

apid

-0.13

_depth

-0.13

 Oswald

-0.13

yny

-0.13

POSITIVE LOGITS

 illeg

0.15

NCY

0.15

IData

0.14

ÐµÑģÑı

0.14

llen

0.14

 chuck

0.14

alic

0.13

hsi

0.13

uur

0.13

Activations Density 0.018%

references to programming languages and associated libraries

No Comments

No Known Activations