INDEX

Explanations

actions and phrases related to helping, improving, and evaluating processes or situations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

oir

-0.16

ÙĪÙĦÙĩ

-0.15

ariance

-0.15

Ø·ØŃ

-0.15

.createClass

-0.15

ueva

-0.15

anÄ±

-0.15

ÏģÎ¹Î¬

-0.14

StackNavigator

-0.14

åģ

-0.14

POSITIVE LOGITS

à¸ģà¸£à¸£à¸¡

0.16

 importantly

0.15

etc

0.14

gal

0.14

 overall

0.14

URRE

0.14

Restricted

0.14

 willing

0.14

 Presidential

0.13

Dal

0.13

Activations Density 0.322%

actions and phrases related to helping, improving, and evaluating processes or situations

No Comments

No Known Activations