INDEX

Explanations

references to scientific concepts and academic credentials

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

idd

-0.14

ÃĹ↵↵

-0.14

sockopt

-0.13

classCallCheck

-0.13

zÄħd

-0.13

xDA

-0.13

 Defense

-0.13

encv

-0.13

.onView

-0.13

POSITIVE LOGITS

kaz

0.14

ä½Ļ

0.14

 TMPro

0.14

vant

0.14

ichen

0.14

.*(

0.13

 siden

0.13

akhir

0.13

kel

0.13

Ã©lÃ©

0.13

Activations Density 0.630%

references to scientific concepts and academic credentials

No Comments

No Known Activations