INDEX

Explanations

instances of reported speech or quotations in the text

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

ora

-0.18

pole

-0.17

quette

-0.17

oras

-0.16

ORA

-0.16

ove

-0.15

aga

-0.15

 éĻ

-0.15

Ã¼tÃ¼n

-0.14

 pole

-0.14

POSITIVE LOGITS

abler

0.16

pog

0.15

kart

0.15

ãĤĵãģ¨

0.15

avern

0.15

ipple

0.14

kowski

0.14

æķ

0.14

aman

0.14

aylor

0.14

Activations Density 0.135%

instances of reported speech or quotations in the text

No Comments

No Known Activations