INDEX

Explanations

references to quantities, specifically those involving large numbers or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

tram

-0.15

OLON

-0.14

aji

-0.14

UY

-0.14

_android

-0.14

uÃ©

-0.14

jective

-0.13

 Harmony

-0.13

emachine

-0.13

Ð¾Ð½ÑĮ

-0.13

POSITIVE LOGITS

day

0.17

 year

0.16

 month

0.16

uda

0.16

-day

0.15

 annum

0.15

UpDown

0.15

aler

0.14

ÌĢ

0.14

Ø²Ø§

0.14

Activations Density 0.016%

references to quantities, specifically those involving large numbers or measurements

No Comments

No Known Activations