INDEX

Explanations

references to phone calls and contact information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Telefon

-0.26

 telefon

-0.25

telephone

-0.24

 telephone

-0.24

-phone

-0.23

 phone

-0.23

tele

-0.23

phone

-0.23

 Telephone

-0.22

 tele

-0.22

POSITIVE LOGITS

 Toll

0.28

 toll

0.25

DID

0.23

NAN

0.23

 Forward

0.22

 Vanity

0.22

 forward

0.21

prefix

0.20

_forward

0.20

 prefix

0.20

Activations Density 0.021%

references to phone calls and contact information

No Comments

No Known Activations