INDEX

Explanations

references to infrastructure projects and improvements

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ertas

-0.14

Ã¦r

-0.14

 Ð´Ð¾Ðº

-0.14

_CLEAN

-0.13

IRECT

-0.13

AGMA

-0.12

Ĺi

-0.12

tered

-0.12

)((((

-0.12

ogy

-0.12

POSITIVE LOGITS

 Schwar

0.15

rian

0.15

 Level

0.14

IDEO

0.14

 smooth

0.14

·»

0.14

à¸«à¸¥à¸§à¸ĩ

0.14

 trunk

0.13

"default

0.13

OMX

0.13

Activations Density 0.395%

references to infrastructure projects and improvements

No Known Activations