INDEX

Explanations

instances of humor and expressions of laughter

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

uzzi

-0.18

uja

-0.16

.bundle

-0.15

ìĦĿ

-0.15

Taj

-0.15

arda

-0.15

aj

-0.15

lep

-0.14

aji

-0.14

izzling

-0.14

POSITIVE LOGITS

ast

0.21

ast

0.21

asts

0.21

Ast

0.20

Ast

0.19

astro

0.19

Danny

0.17

 astro

0.17

 Astro

0.17

(ast

0.17

Activations Density 0.028%

instances of humor and expressions of laughter

No Comments

No Known Activations