INDEX

Explanations

references to entities or categories within content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Bun

-0.17

ArrayOf

-0.15

incer

-0.14

eve

-0.14

æ²¢

-0.14

olini

-0.14

aginator

-0.14

 Skip

-0.13

vs

-0.13

 Drag

-0.13

POSITIVE LOGITS

uae

0.14

.carousel

0.14

elson

0.14

DMI

0.14

iot

0.13

Hoy

0.13

ocoder

0.13

iosa

0.13

à¤ļà¤¨

0.13

bare

0.13

Activations Density 0.000%

references to entities or categories within content

No Comments

No Known Activations