INDEX

Explanations

references to dates and numerical values related to time or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

igth

-0.16

elter

-0.15

rish

-0.15

itchens

-0.15

ÅĻÃ¡d

-0.15

Ð¾Ð¿Ð¾Ð»

-0.14

 éĦ

-0.14

Ð¾ÐºÐ¾Ð½

-0.14

loven

-0.14

Ã©rc

-0.14

POSITIVE LOGITS

quir

0.17

azon

0.16

alias

0.15

quil

0.15

 vars

0.14

zug

0.14

 complet

0.14

åįļå£«

0.13

aliases

0.13

Activations Density 0.024%

references to dates and numerical values related to time or events

No Comments

No Known Activations