INDEX

Explanations

references to the name "Yan" and its variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

chet

-0.19

emons

-0.15

ieu

-0.14

lyn

-0.14

 DISCLAIM

-0.14

achs

-0.14

onte

-0.14

ÐµÐºÑĤÐ¸Ð²

-0.14

apos

-0.14

ifton

-0.14

POSITIVE LOGITS

kees

0.18

agi

0.17

kee

0.16

 fact

0.15

Mim

0.15

 ÙĦÙĨ

0.14

lÄ±ÅŁ

0.14

amoto

0.14

beck

0.14

SHARE

0.14

Activations Density 0.018%

references to the name "Yan" and its variants

No Comments

No Known Activations