INDEX

Explanations

references to organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

.scalablytyped

-0.15

hir

-0.14

 Walton

-0.14

OTO

-0.14

weed

-0.14

 Savage

-0.13

 Lion

-0.13

.JPG

-0.13

 Swan

-0.13

POSITIVE LOGITS

/apache

0.18

 apache

0.17

.apache

0.17

.springframework

0.17

Apache

0.16

.slf

0.16

apache

0.16

 mour

0.16

ÑĢÑİ

0.15

iller

0.15

Activations Density 0.013%

references to organizations

No Comments

No Known Activations