INDEX

Explanations

references to news or sports articles from "USA Today."

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

equ

-0.19

aine

-0.16

vit

-0.15

Ãºi

-0.15

ic

-0.14

 Noble

-0.14

ied

-0.14

init

-0.14

eth

-0.14

anes

-0.14

POSITIVE LOGITS

.habbo

0.15

ette

0.15

qli

0.15

cape

0.15

 ==============================================================

0.14

chemy

0.14

ÑĢÐ¾Ð²Ð¸Ñĩ

0.14

 Ð°ÐºÑĤÐ¸

0.14

lisi

0.14

OLA

0.13

Activations Density 0.002%

references to news or sports articles from "USA Today."

No Comments

No Known Activations