INDEX

Explanations

terms associated with prestigious awards and honors

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

 Ø§ÙĦØ¹Ø±Ø¨ÙĬØ©

-0.15

iqu

-0.15

ERA

-0.14

 Rubin

-0.14

ToFront

-0.14

 Essential

-0.14

±

-0.13

iesen

-0.13

cmb

-0.13

POSITIVE LOGITS

ÅĻi

0.17

elite

0.16

ders

0.16

Ã³Å¼

0.16

dro

0.15

reserved

0.15

zy

0.15

 reserved

0.15

reen

0.15

istine

0.15

Activations Density 0.025%

terms associated with prestigious awards and honors

No Comments

No Known Activations