INDEX

Explanations

structured data formats and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

cor

-0.16

qu

-0.16

 writ

-0.15

 upside

-0.15

opp

-0.15

-0.14

POSITIVE LOGITS

rien

0.19

.GetCurrent

0.16

@nate

0.16

.mousePosition

0.14

 ReturnValue

0.14

aine

0.14

bitrary

0.14

ÑģÑĭÐ»ÐºÐ¸

0.14

akra

0.14

Activations Density 0.050%

structured data formats and attributes

No Comments

No Known Activations