INDEX

Explanations

references to popular television shows and characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

_DF

-0.15

kus

-0.15

à¤¾à¤¨à¤®

-0.15

 addCriterion

-0.15

yms

-0.14

elry

-0.14

inand

-0.14

getRow

-0.14

upos

-0.14

ustry

-0.14

POSITIVE LOGITS

 fore

0.22

 Fore

0.20

NC

0.18

Fore

0.18

NC

0.17

 FORE

0.17

olland

0.16

agent

0.16

fore

0.15

ensi

0.15

Activations Density 0.049%

references to popular television shows and characters

No Comments

No Known Activations