INDEX

Explanations

HTML and XML tags or elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

lesia

-0.15

 putas

-0.14

Ã¤chst

-0.14

 Wheel

-0.13

 Break

-0.13

.struts

-0.13

hani

-0.13

âĶĶ

-0.13

anja

-0.13

utschein

-0.12

POSITIVE LOGITS

_BS

0.14

aced

0.14

Bluetooth

0.13

 JNICALL

0.13

 Accord

0.13

 Sever

0.13

APH

0.12

 elev

0.12

smarty

0.12

Activations Density 0.554%

HTML and XML tags or elements

No Comments

No Known Activations