INDEX

Explanations

dates and ordinal numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ç¨±

-0.16

 called

-0.16

 Called

-0.16

erc

-0.16

 Holl

-0.15

eri

-0.15

ç§°

-0.15

called

-0.15

çĭ¼

-0.15

erg

-0.14

POSITIVE LOGITS

umes

0.17

stan

0.16

hausen

0.15

UME

0.15

burgh

0.15

ume

0.14

argin

0.14

 searchable

0.14

 Roths

0.14

sector

0.14

Activations Density 0.114%

dates and ordinal numbers

No Comments

No Known Activations