INDEX

Explanations

elements related to document formatting and structural integrity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 EITHER

-0.16

Ã´t

-0.16

 either

-0.15

either

-0.15

ee

-0.15

 Victor

-0.14

AND

-0.14

quam

-0.14

 ê³§

-0.14

Obr

-0.13

POSITIVE LOGITS

etc

0.60

etc

0.48

çŃī

0.36

/etc

0.34

ãģªãģ©

0.33

 ÑĤÐ¾ÑīÐ¾

0.33

 çŃī

0.32

ãģªãģ©ãģ®

0.30

 ëĵ±

0.30

 ëĵ±ìĿĦ

0.29

Activations Density 0.215%

elements related to document formatting and structural integrity

No Comments

No Known Activations