INDEX

Explanations

phrases indicating degrees or levels of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ãĤ«ãĥ¼

-0.16

izar

-0.15

 kara

-0.14

odem

-0.14

trad

-0.14

 Pace

-0.14

.nlm

-0.14

sing

-0.13

ois

-0.13

undy

-0.13

POSITIVE LOGITS

ENS

0.16

anos

0.15

Ach

0.14

 slightly

0.14

ÙģØ§ÙĤ

0.14

Ã«r

0.13

atti

0.13

ÑĦÐ¾ÑĢ

0.13

 Morales

0.13

ey

0.13

Activations Density 0.033%

phrases indicating degrees or levels of something

No Comments

No Known Activations