INDEX

Explanations

sequences of formatting characters or symbols in technical documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

erna

-0.19

Ø§ÙĨÙĩ

-0.16

ationship

-0.16

erm

-0.16

ses

-0.16

irie

-0.15

ãĥ«ãĥķ

-0.15

entials

-0.15

Ð¼Ð¾Ð²ÑĸÑĢ

-0.14

áº±m

-0.14

POSITIVE LOGITS

kwargs

0.24

*(

0.21

*/

0.21

*>

0.20

*)

0.19

ÂłÂłÂłÂłÂł

0.18

ician

0.18

ÂłÂłÂłÂłÂłÂłÂł

0.18

ÂłÂłÂłÂłÂłÂłÂłÂł

0.18

/***

0.17

Activations Density 0.041%

sequences of formatting characters or symbols in technical documentation

No Comments

No Known Activations