INDEX

Explanations

numerical information and dates related to events

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

gii

-0.15

finger

-0.14

ØŃØ¨

-0.14

Ø´ÙħØ§ÙĦÛĮ

-0.14

ÑĥÐºÐ°

-0.14

zim

-0.14

ueur

-0.13

 MÃ£

-0.13

POSITIVE LOGITS

appa

0.15

ê´

0.15

immel

0.14

æĶ¶åħ¥

0.14

dev

0.14

anton

0.14

çĿĢ

0.14

trand

0.13

ichen

0.13

 Licence

0.13

Activations Density 0.019%

numerical information and dates related to events

No Comments

No Known Activations