INDEX

Explanations

references to items that are covered or coated in specific materials, particularly in a descriptive context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ahun

-0.18

nech

-0.17

asal

-0.15

æĶ¶å½ķ

-0.15

lico

-0.15

TagName

-0.15

vatel

-0.14

 Ø§ÙĦÙħÙĥ

-0.14

==>

-0.14

POSITIVE LOGITS

 something

0.17

 strings

0.16

 layers

0.15

 ISSN

0.15

by

0.15

util

0.15

 either

0.15

ro

0.14

Activations Density 0.197%

references to items that are covered or coated in specific materials, particularly in a descriptive context

No Comments

No Known Activations