INDEX

Explanations

the word "Kun" and its variations

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

istrovstvÃŃ

-0.19

anagan

-0.16

ÅĻaz

-0.15

à¸£à¸¡

-0.15

 bilm

-0.14

FML

-0.14

orney

-0.14

cly

-0.14

hind

-0.14

oons

-0.14

POSITIVE LOGITS

à¥įà¤¹

0.15

uzu

0.15

ibre

0.15

iew

0.14

nn

0.14

forder

0.14

à¥Ģà¤ĸ

0.14

ifold

0.14

apest

0.14

ighbour

0.14

Activations Density 0.060%

the word "Kun" and its variations

No Comments

No Known Activations