INDEX

Explanations

statements or phrases that express intrigue or captivate attention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ovic

-0.17

enschaft

-0.16

ISR

-0.15

rots

-0.14

 Leban

-0.14

ÑĥÐ½Ðº

-0.14

Ð¾Ð²Ð¾

-0.14

Ä¢

-0.14

Ø§Ø°

-0.14

animated

-0.13

POSITIVE LOGITS

Ð°ÑĢÑĮ

0.16

unar

0.15

ijken

0.15

 Williamson

0.14

ORM

0.14

&);↵↵

0.14

 Stam

0.14

Å¼

0.14

elay

0.14

so

0.13

Activations Density 0.124%

statements or phrases that express intrigue or captivate attention

No Comments

No Known Activations