INDEX

Explanations

locations and geographical references

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

roj

-0.15

.tm

-0.15

Î¿Îº

-0.14

 Hindered

-0.14

pNet

-0.13

.decorate

-0.13

_basic

-0.13

ltk

-0.13

uyá»ĩn

-0.13

 ucfirst

-0.13

POSITIVE LOGITS

 Drive

0.39

 Avenue

0.36

 Street

0.36

 Road

0.36

Ave

0.36

Way

0.34

Rd

0.33

 Boulevard

0.31

 street

0.31

 Court

0.31

Activations Density 0.151%

locations and geographical references

No Comments

No Known Activations