INDEX

Explanations

references to blogs and blogging activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

lings

-0.15

liste

-0.15

gent

-0.15

neas

-0.15

inel

-0.14

urses

-0.14

Kok

-0.14

ÑĥÐºÐ¸

-0.14

okers

-0.14

eft

-0.14

POSITIVE LOGITS

spot

0.18

.crm

0.17

arith

0.17

azon

0.17

gers

0.16

astro

0.15

 Gast

0.15

iversary

0.15

overn

0.14

/video

0.14

Activations Density 0.023%

references to blogs and blogging activities

No Comments

No Known Activations