INDEX

Explanations

expressions of complexity and contradiction in human experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

.AD

-0.17

aku

-0.16

ä»ĭ

-0.16

 buckle

-0.14

/std

-0.14

lug

-0.13

.experimental

-0.13

moduleId

-0.13

XS

-0.13

POSITIVE LOGITS

ongyang

0.15

olet

0.15

 å¤ª

0.15

olean

0.15

heels

0.15

cket

0.14

ying

0.14

too

0.14

ket

0.14

usi

0.14

Activations Density 0.147%

expressions of complexity and contradiction in human experiences

No Comments

No Known Activations