INDEX

Explanations

numerical values and quantities related to time and measurements

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

airo

-0.17

rosso

-0.14

kud

-0.14

erval

-0.14

illance

-0.13

 Hend

-0.13

 tipping

-0.13

ÎµÎ¹Î¿

-0.13

ERRY

-0.13

lobs

-0.13

POSITIVE LOGITS

dap

0.17

 Bans

0.16

angu

0.16

zan

0.15

xiv

0.15

alon

0.15

arehouse

0.14

icer

0.14

reat

0.14

Activations Density 0.112%

numerical values and quantities related to time and measurements

No Comments

No Known Activations