INDEX

Explanations

code related to Google Maps API functionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

-0.15

 certain

-0.14

ideographic

-0.14

closure

-0.14

çħ

-0.14

lah

-0.14

/tty

-0.14

Ø´ÛĮ

-0.14

vas

-0.13

POSITIVE LOGITS

ERTICAL

0.16

èĪ

0.15

arten

0.14

upert

0.14

 sacr

0.14

achel

0.14

imed

0.14

burgh

0.14

iosk

0.13

Activations Density 0.095%

code related to Google Maps API functionality

No Comments

No Known Activations