INDEX

Explanations

content related to user interactions and blog post formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

lew

-0.15

 signatures

-0.15

.enumer

-0.14

het

-0.14

Å¡ti

-0.14

Contract

-0.14

åı¬

-0.14

elpers

-0.14

ret

-0.13

Avatar

-0.13

POSITIVE LOGITS

riott

0.15

 Slov

0.15

enson

0.14

omat

0.14

_void

0.14

elah

0.14

 Morav

0.14

itespace

0.14

 manifest

0.14

Activations Density 0.074%

content related to user interactions and blog post formatting

No Comments

No Known Activations