INDEX

Explanations

instances of the word "free" and related terms indicating complimentary offers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 pricey

-0.16

ibo

-0.15

ÑĢÐ°Ð²Ð°

-0.15

que

-0.14

rece

-0.14

xca

-0.14

ns

-0.14

pike

-0.14

wn

-0.14

POSITIVE LOGITS

bies

0.42

bie

0.40

zes

0.24

-standing

0.24

zers

0.22

-of

0.21

bsd

0.21

zing

0.21

 trials

0.21

ze

0.20

Activations Density 0.035%

instances of the word "free" and related terms indicating complimentary offers

No Comments

No Known Activations