INDEX

Explanations

instances of the word "place."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

erson

-0.15

áº¯ng

-0.15

urette

-0.14

immel

-0.14

Byl

-0.14

Kat

-0.14

amage

-0.14

 ÑģÐ¿Ð°Ñģ

-0.14

Kat

-0.14

arty

-0.14

POSITIVE LOGITS

ç¹

0.14

 nIndex

0.14

asic

0.14

åĸľ

0.14

ion

0.14

omanip

0.13

TION

0.13

ãģĲ

0.13

 Elijah

0.13

ate

0.13

Activations Density 0.007%

instances of the word "place."

No Comments

No Known Activations