INDEX

Explanations

terms related to publishing, including references to publication details and book-related information

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

imbus

-0.16

nap

-0.16

ania

-0.15

Î¹Ïĥ

-0.15

avl

-0.14

ÚĺÙĩ

-0.14

 Ð½Ð°Ð¿

-0.14

 Prior

-0.14

alk

-0.14

hang

-0.13

POSITIVE LOGITS

zell

0.16

embedding

0.14

 Castro

0.14

 Ð´Ð²Ð¾ÑĢ

0.14

mma

0.14

.FontStyle

0.14

 downtown

0.14

igy

0.14

quate

0.13

ãĥ³ãĤ°ãĥ«

0.13

Activations Density 0.228%

terms related to publishing, including references to publication details and book-related information

No Comments

No Known Activations