INDEX

Explanations

assignment or initialization statements in code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ellen

-0.15

ogue

-0.15

essler

-0.14

antro

-0.14

Ben

-0.14

asse

-0.14

lez

-0.14

 Blond

-0.14

 Deals

-0.14

/pass

-0.13

POSITIVE LOGITS

.Generated

0.16

rud

0.15

Ð°ÑĢÑĩ

0.14

WebService

0.14

egra

0.14

haar

0.14

eniable

0.14

IDO

0.14

Activations Density 0.003%

assignment or initialization statements in code

No Comments

No Known Activations