INDEX

Explanations

references to the "Horizon" series and its updates or components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Ã©gor

-0.17

enta

-0.15

Ð°Ð±Ð¾

-0.15

oppel

-0.15

ASTE

-0.15

¯

-0.14

kins

-0.14

ora

-0.13

ande

-0.13

éĢł

-0.13

POSITIVE LOGITS

arium

0.19

ulum

0.15

adow

0.15

0.14

ç¨¿

0.14

iaux

0.14

æŁľ

0.14

äº«

0.14

joy

0.13

Hem

0.13

Activations Density 0.005%

references to the "Horizon" series and its updates or components

No Comments

No Known Activations