INDEX

Explanations

evaluative and comparative adjectives related to size and significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ROM

-0.15

fik

-0.15

uj

-0.15

 BÃ¶yle

-0.14

anj

-0.14

achten

-0.14

_SIG

-0.14

á»ĳt

-0.14

 Oyun

-0.13

ract

-0.13

POSITIVE LOGITS

yet

0.19

yet

0.18

possible

0.17

 possible

0.17

Yet

0.16

 aller

0.15

 amongst

0.15

 imaginable

0.15

åİ

0.15

à¤¾à¤Ĭ

0.15

Activations Density 0.409%

evaluative and comparative adjectives related to size and significance

No Comments

No Known Activations