INDEX

Explanations

words related to usage and operational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Uvs

-0.17

Ð»ÑĸÐ´

-0.15

noinspection

-0.15

 ThemeData

-0.15

mÃŃ

-0.15

 pend

-0.15

isco

-0.14

»¿

-0.14

nex

-0.13

.uk

-0.13

POSITIVE LOGITS

 Pentagon

0.16

 Bush

0.15

åħ

0.15

?type

0.15

SIG

0.14

ÃŃÅ¡

0.14

amedi

0.14

 setuptools

0.14

voje

0.13

coli

0.13

Activations Density 0.000%

words related to usage and operational contexts

No Comments

No Known Activations