INDEX

Explanations

phrases related to change and transformation

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

gger

-0.16

ÅĽ

-0.15

ectors

-0.14

åĴ²

-0.14

iev

-0.14

/or

-0.14

wards

-0.14

&#

-0.13

ille

-0.13

adium

-0.13

POSITIVE LOGITS

0.15

Carthy

0.14

udic

0.14

_SUPPLY

0.14

Drv

0.14

/generated

0.13

ìĸ´

0.13

Ð¶Ð½Ð¾

0.13

pill

0.13

riot

0.13

Activations Density 0.631%

phrases related to change and transformation

No Comments

No Known Activations