INDEX

Explanations

instructions related to navigating and managing digital platforms or interfaces

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

pic

-0.17

metic

-0.15

ding

-0.15

_DGRAM

-0.14

ghi

-0.14

_DEPRECATED

-0.14

Ã©rc

-0.14

ĽĦ

-0.13

Vis

-0.13

uncios

-0.13

POSITIVE LOGITS

 https

0.23

 http

0.23

www

0.16

http

0.16

andr

0.16

https

0.16

 Saunders

0.15

_https

0.15

atham

0.15

,www

0.15

Activations Density 0.050%

instructions related to navigating and managing digital platforms or interfaces

No Comments

No Known Activations