INDEX

Explanations

sections of text that describe existence or presence, emphasizing quantities and types of entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

arah

-0.17

 dist

-0.16

 Dist

-0.15

åºĥ

-0.15

adr

-0.14

/dist

-0.14

otic

-0.14

.application

-0.14

_ru

-0.13

anko

-0.13

POSITIVE LOGITS

ÙģØµÙĦ

0.15

fad

0.14

zon

0.14

 intestine

0.14

vary

0.14

fal

0.14

oux

0.14

ilton

0.14

ÄĽn

0.13

anca

0.13

Activations Density 0.104%

sections of text that describe existence or presence, emphasizing quantities and types of entities

No Comments

No Known Activations