INDEX

Explanations

instances involving witness accounts or observations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Bilg

-0.15

èªł

-0.14

gs

-0.14

.ua

-0.14

ovsky

-0.14

ÅĽnie

-0.14

 ÐĴÐ¸Ðº

-0.14

à¸¡à¸Ļ

-0.14

pawn

-0.13

 pant

-0.13

POSITIVE LOGITS

uche

0.16

/Dk

0.15

blind

0.15

 íĦ°

0.14

rlen

0.14

aÅ¼

0.14

 Partition

0.14

 partitions

0.14

jem

0.14

Activations Density 0.252%

instances involving witness accounts or observations

No Known Activations