INDEX

Explanations

words and phrases indicating attendance and presence at events

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

Not in Any Lists

No Comments

Negative Logits

abet

-0.15

ivet

-0.14

agrams

-0.14

alendar

-0.14

HEME

-0.14

ides

-0.14

vie

-0.13

Ã¨ve

-0.13

onom

-0.13

.tools

-0.13

POSITIVE LOGITS

aille

0.16

cene

0.15

ì¹ĺ

0.15

 åĿ

0.14

ILA

0.14

/MPL

0.13

 horn

0.13

å½¦

0.13

Ð½Ð¸ÑĤ

0.13

itez

0.13

Activations Density 0.115%

words and phrases indicating attendance and presence at events

No Comments

No Known Activations