INDEX

Explanations

references to the learning process and challenges associated with adopting new software or technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

illez

-0.16

 GÃ¼r

-0.15

erli

-0.15

ulus

-0.15

dete

-0.14

dio

-0.14

ç«¥

-0.14

 '..',

-0.14

Maker

-0.13

obr

-0.13

POSITIVE LOGITS

 USAGE

0.15

 Usage

0.15

rets

0.15

 usage

0.15

 misuse

0.14

Sez

0.14

 Spoon

0.14

SEX

0.14

ounty

0.14

thur

0.14

Activations Density 0.231%

references to the learning process and challenges associated with adopting new software or technology

No Comments

No Known Activations