INDEX

Explanations

phrases related to awards and recognitions

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

å±±å¸Ĥ

-0.14

afone

-0.14

odox

-0.13

è³Ģ

-0.13

chner

-0.13

.wikipedia

-0.13

antas

-0.13

éľ

-0.13

 Glas

-0.13

arters

-0.13

POSITIVE LOGITS

Ð°Ð¼Ð¿

0.20

 DÃ¼n

0.16

 hang

0.14

_macro

0.14

hang

0.13

oning

0.13

æĥħ

0.13

itere

0.13

lere

0.13

opia

0.13

Activations Density 0.057%

phrases related to awards and recognitions

No Comments

No Known Activations