INDEX

Explanations

fragments or elements in text that suggest emphasis or quotes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

orr

-0.18

 Nich

-0.15

aterno

-0.15

aison

-0.14

Î¹ÎºÎ¬

-0.14

ire

-0.14

ÑĥÐ¼Ð¾Ð²

-0.14

ickey

-0.14

amina

-0.14

Haz

-0.14

POSITIVE LOGITS

GH

0.15

emony

0.15

.cf

0.15

HostException

0.14

ç¥

0.14

reeze

0.14

(æľĪ

0.14

reshape

0.14

.ini

0.14

Mini

0.14

Activations Density 0.007%

fragments or elements in text that suggest emphasis or quotes

No Comments

No Known Activations