INDEX

Explanations

references to business-related topics or entities

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

ichel

-0.16

contr

-0.15

á¿¶

-0.15

unch

-0.15

dr

-0.15

ksam

-0.15

 contr

-0.15

rouch

-0.14

.lu

-0.14

POSITIVE LOGITS

ares

0.16

owan

0.16

arel

0.16

ongan

0.15

 Kernel

0.15

 Sous

0.15

OU

0.14

aat

0.14

_fraction

0.14

Activations Density 0.015%

references to business-related topics or entities

No Comments

No Known Activations