INDEX

Explanations

references to significant legal or governmental actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

helper

-0.14

à¸£à¸£

-0.14

hyp

-0.14

èŀį

-0.13

Ð²Ð¸Ð½

-0.13

á»¥c

-0.13

 hired

-0.13

ãĥªãĥ¼ãĤº

-0.13

 Voll

-0.13

ÎµÎ¹Î¿

-0.13

POSITIVE LOGITS

His

0.50

His

0.42

Her

0.34

 ÐķÐ³Ð¾

0.31

HIS

0.28

HE

0.28

 Excell

0.27

Her

0.27

HH

0.26

HR

0.25

Activations Density 0.248%

references to significant legal or governmental actions

No Comments

No Known Activations