INDEX

Explanations

references to notable individuals and institutions, particularly in the context of culture and history

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

iskey

-0.18

ataka

-0.17

Spoiler

-0.15

itori

-0.14

ØªØ¨

-0.14

antine

-0.14

Spo

-0.14

 spoiler

-0.14

ModelProperty

-0.13

istrate

-0.13

POSITIVE LOGITS

[--

0.16

usher

0.16

cape

0.15

enberg

0.15

ÐĲÑĢÑħÑĸÐ²

0.14

 Jennings

0.14

SENS

0.14

 Ð²Ð¾Ð²

0.14

tay

0.14

.getSystemService

0.14

Activations Density 0.539%

references to notable individuals and institutions, particularly in the context of culture and history

No Comments

No Known Activations