INDEX

Explanations

elements related to configuration options or settings within a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

çĳ

-0.14

pan

-0.14

insics

-0.14

minent

-0.14

Ã¡b

-0.13

ead

-0.13

eniable

-0.13

Ãłm

-0.13

bjerg

-0.13

 infinity

-0.13

POSITIVE LOGITS

.scalablytyped

0.17

\:

0.16

 miscellaneous

0.15

Ø§ÙĤ

0.15

ammers

0.15

Rat

0.14

 ment

0.14

ac

0.13

Vig

0.13

 numberOfRowsInSection

0.13

Activations Density 0.025%

elements related to configuration options or settings within a technical context

No Comments

No Known Activations