INDEX

Explanations

adjectives and descriptors related to quality and features of products or experiences

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

ani

-0.18

.scalablytyped

-0.17

lund

-0.16

jen

-0.15

vil

-0.15

-0.14

agram

-0.14

iley

-0.14

abyrinth

-0.14

POSITIVE LOGITS

omite

0.17

 Bust

0.14

igne

0.14

occo

0.14

Forgery

0.14

ovaly

0.14

alim

0.13

cou

0.13

 Larry

0.13

 ((__

0.13

Activations Density 0.253%

adjectives and descriptors related to quality and features of products or experiences

No Comments

No Known Activations