INDEX

Explanations

specific nouns and phrases related to various fields and contexts, such as industries, education, food, and social issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ÑĤÐ°Ð¶

-0.15

izzas

-0.14

aea

-0.14

.gdx

-0.14

æĪ·

-0.13

ueva

-0.13

xmax

-0.13

ICENSE

-0.13

awe

-0.13

.JPG

-0.13

POSITIVE LOGITS

ARP

0.15

ellen

0.15

anship

0.15

 ëĵ±ìĿĦ

0.14

 importantly

0.14

ÃĹ↵↵

0.14

ÙĬØ±Ø©

0.14

etc

0.14

etc

0.13

 neutrality

0.13

Activations Density 0.306%

specific nouns and phrases related to various fields and contexts, such as industries, education, food, and social issues

No Comments

No Known Activations