INDEX

Explanations

phrases related to options and choices available to individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ofil

-0.17

vra

-0.15

áº¡i

-0.14

gers

-0.14

icont

-0.14

edin

-0.14

rais

-0.14

åĳ¼

-0.13

eba

-0.13

antee

-0.13

POSITIVE LOGITS

 options

0.47

options

0.37

 option

0.36

 Options

0.35

/options

0.34

 alternatives

0.32

 choices

0.31

Options

0.31

 OPTIONS

0.30

(options

0.30

Activations Density 0.092%

phrases related to options and choices available to individuals

No Comments

No Known Activations