INDEX

Explanations

punctuation marks and their arrangement within sentences

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

icorn

-0.19

templ

-0.19

uzey

-0.16

-0.14

uale

-0.14

uales

-0.14

urm

-0.14

 nghiá»ĩp

-0.14

ymes

-0.14

ÃŃky

-0.14

POSITIVE LOGITS

Ģ

0.14

inha

0.14

ÑĢÑıÐ´

0.14

 Shay

0.13

oxy

0.13

ÏĥÎºÎµ

0.13

 Prescott

0.13

 Cush

0.13

man

0.13

 Burl

0.13

Activations Density 0.039%

punctuation marks and their arrangement within sentences

No Comments

No Known Activations