INDEX

Explanations

references to achievements or titles in sports or competitions, particularly those related to being a champion or winner

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

ÑĢÐ°Ð²Ð°

-0.19

InParameter

-0.18

Ð²Ð¾Ñİ

-0.16

Ã¤Ã¤n

-0.14

_timing

-0.14

enser

-0.14

 Blasio

-0.14

isco

-0.14

stvo

-0.14

ä¾ĭ

-0.14

POSITIVE LOGITS

orges

0.17

Ä±t

0.14

orado

0.14

ocuk

0.14

usb

0.14

 supplied

0.14

à¸°

0.13

gl

0.13

Activations Density 0.006%

references to achievements or titles in sports or competitions, particularly those related to being a champion or winner

No Comments

No Known Activations