INDEX

Explanations

numerical codes or identifiers along with references to trademarks or legal aspects

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

itas

-0.15

ordion

-0.15

éļ

-0.14

 fair

-0.14

lie

-0.14

eÃ§

-0.14

rians

-0.14

cps

-0.14

wal

-0.14

Ø·Ùħ

-0.14

POSITIVE LOGITS

ãĤīãģĹ

0.17

à¤ķà¤¨

0.15

Ð¾Ð»Ð¾

0.15

olo

0.14

Ø§Ø¹Ø¯Ø©

0.14

Ø§Ø²Ùĩ

0.14

ocu

0.14

apl

0.14

 SEEK

0.14

cee

0.14

Activations Density 0.001%

numerical codes or identifiers along with references to trademarks or legal aspects

No Comments

No Known Activations