INDEX

Explanations

references to groups, teams, or ensembles in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

uddy

-0.17

baugh

-0.15

ÑĢÐ°Ð¿

-0.14

otics

-0.14

Hoy

-0.14

ä¼ı

-0.14

bun

-0.14

.Logic

-0.13

Technical

-0.13

 Technical

-0.13

POSITIVE LOGITS

 Affero

0.15

 Cler

0.15

 Hanging

0.15

SingleOrDefault

0.15

INY

0.14

ctl

0.14

Ãªt

0.14

çīĮ

0.14

\Lib

0.13

YRO

0.13

Activations Density 0.240%

references to groups, teams, or ensembles in various contexts

No Comments

No Known Activations