INDEX

Explanations

punctuation and sentence structures with variations in emphasis or tone

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

/*č↵

-0.18

eci

-0.17

ÐµÐ»Ñı

-0.17

alis

-0.16

ÐµÐ»ÐµÐ¹

-0.15

asurer

-0.15

ÙĦÙħ

-0.15

alus

-0.14

ILLISECONDS

-0.14

 moci

-0.14

POSITIVE LOGITS

imir

0.16

æŀ¶

0.15

ma

0.15

 Cumberland

0.14

ahl

0.14

Î¯Î¿Ïħ

0.14

ucky

0.14

 inversion

0.14

 distortion

0.14

MA

0.13

Activations Density 0.000%

punctuation and sentence structures with variations in emphasis or tone

No Comments

No Known Activations