INDEX

Explanations

terminology related to disruptions and disturbances in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

osemite

-0.17

rees

-0.16

haul

-0.15

DonaldTrump

-0.15

finity

-0.15

itud

-0.14

IRCLE

-0.14

play

-0.14

igar

-0.14

ilon

-0.14

POSITIVE LOGITS

/dist

0.19

/conf

0.17

/error

0.17

ometer

0.15

-free

0.15

/dev

0.14

 Chain

0.14

rega

0.14

íİ¸

0.13

ÌĪ

0.13

Activations Density 0.240%

terminology related to disruptions and disturbances in various contexts

No Comments

No Known Activations