INDEX

Explanations

conditional phrases and questions regarding willingness or possibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Ø¦Øª

-0.14

eec

-0.14

neh

-0.14

ÏĦÎ¿Î½

-0.14

lify

-0.14

Ð²Ð°Ð½Ð¾Ð²

-0.14

trusted

-0.13

ãģ¨ãģĨ

-0.13

arkin

-0.13

istani

-0.13

POSITIVE LOGITS

 anyone

0.37

 anybody

0.36

 there

0.30

 Anyone

0.29

 anything

0.28

any

0.26

0.25

Anyone

0.24

any

0.24

Any

0.22

Activations Density 0.181%

conditional phrases and questions regarding willingness or possibility

No Comments

No Known Activations