INDEX

Explanations

references to British entities or subjects

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

mund

-0.16

ulus

-0.15

conde

-0.15

hle

-0.15

indent

-0.14

opa

-0.14

ephy

-0.14

.hu

-0.14

ilit

-0.14

åħ·

-0.14

POSITIVE LOGITS

 Isles

0.26

 Columbia

0.23

 Colum

0.19

 Virgin

0.19

 Airways

0.17

ness

0.16

olumbia

0.15

gow

0.15

 Honduras

0.15

 Britt

0.15

Activations Density 0.023%

references to British entities or subjects

No Comments

No Known Activations

references to British entities or subjects

No Comments

No Known Activations