INDEX

Explanations

references to the word "Fort."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

hip

-0.16

GBT

-0.16

Ð´Ð°Ð¿

-0.16

entropy

-0.15

ãģ¾ãģ¾

-0.15

errupt

-0.14

perPage

-0.14

ç¿¼

-0.14

.heroku

-0.14

ings

-0.14

POSITIVE LOGITS

agn

0.17

shire

0.17

smarty

0.16

ains

0.16

lier

0.16

aged

0.15

chet

0.15

aleza

0.15

ainer

0.15

astic

0.15

Activations Density 0.016%

references to the word "Fort."

No Comments

No Known Activations