INDEX

Explanations

references to increasing or enhancing something, particularly in economic or performance contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

aul

-0.19

ationally

-0.17

ken

-0.17

nez

-0.16

ANTS

-0.16

aps

-0.16

Nab

-0.15

idal

-0.15

ãĥªãĥ¼ãĤº

-0.15

OOSE

-0.15

POSITIVE LOGITS

riding

0.19

aroo

0.18

anova

0.16

 morale

0.16

icket

0.15

rong

0.15

sters

0.15

íĦ

0.15

 Binder

0.15

agged

0.14

Activations Density 0.008%

references to increasing or enhancing something, particularly in economic or performance contexts

No Comments

No Known Activations