INDEX

Explanations

terms related to specialized roles or expertise in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

mey

-0.15

Neb

-0.15

ilog

-0.14

uml

-0.14

bsites

-0.14

 herr

-0.14

 DÃ¼n

-0.14

erra

-0.14

ust

-0.13

 Brook

-0.13

POSITIVE LOGITS

anker

0.18

ly

0.17

ness

0.17

Ð´ÐµÐ¼

0.17

YGON

0.16

istically

0.16

cheid

0.16

Ã³nico

0.16

Uvs

0.16

.utility

0.15

Activations Density 0.737%

terms related to specialized roles or expertise in various fields

No Comments

No Known Activations