INDEX

Explanations

references to numerical and statistical data

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ltk

-0.15

abby

-0.14

fwd

-0.14

 GÃ¼r

-0.14

ky

-0.14

 Gast

-0.13

AppName

-0.13

opy

-0.13

Ð½ÑıÑĤ

-0.13

ipy

-0.13

POSITIVE LOGITS

indre

0.17

ç½

0.16

lico

0.16

mans

0.15

eres

0.15

eways

0.15

amak

0.14

ÑĢÐµÐ¹

0.14

undo

0.14

anja

0.14

Activations Density 0.241%

references to numerical and statistical data

No Comments

No Known Activations