INDEX

Explanations

numerical values, particularly statistics or data points

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

 Appeals

-0.15

 MyBase

-0.14

inton

-0.14

aman

-0.14

Ø´ÙħØ§ÙĦÛĮ

-0.13

lua

-0.13

+xml

-0.13

INU

-0.13

POSITIVE LOGITS

udo

0.15

Ð°Ð¹ÑĤ

0.14

 virgin

0.14

unal

0.14

 Gain

0.14

ubern

0.14

petto

0.13

 hook

0.13

datable

0.13

ugin

0.13

Activations Density 0.075%

numerical values, particularly statistics or data points

No Comments

No Known Activations