INDEX

Explanations

references to spinning or rotating actions and mechanics

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

_Lean

-0.16

eway

-0.16

Î¸Î¿

-0.16

ocaly

-0.16

pire

-0.15

ampie

-0.15

lug

-0.15

Ð¸ÑĩÐ°

-0.15

erville

-0.15

_Statics

-0.15

POSITIVE LOGITS

assage

0.14

-around

0.14

umeric

0.14

/flutter

0.14

ä¹¾

0.13

á»ĳc

0.13

-spin

0.13

izzo

0.13

Activations Density 0.068%

references to spinning or rotating actions and mechanics

No Comments

No Known Activations