INDEX

Explanations

dialogue and quotations in texts

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

iw

-0.17

lef

-0.15

RIES

-0.14

overy

-0.14

Rib

-0.14

iris

-0.14

 Oswald

-0.14

usch

-0.13

SSI

-0.13

annis

-0.13

POSITIVE LOGITS

é¹

0.14

Î¸ÎµÎ½

0.13

Ã©k

0.13

 buckle

0.13

ople

0.13

 Mayer

0.13

à¸±à¸¡à¸ŀ

0.13

 loose

0.13

ister

0.13

iges

0.13

Activations Density 0.237%

dialogue and quotations in texts

No Comments

No Known Activations