INDEX

Explanations

key terms related to media coverage and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

rzy

-0.16

forge

-0.15

ArgumentNullException

-0.14

 pudd

-0.14

Cul

-0.14

.Native

-0.14

ycastle

-0.14

bourne

-0.13

lok

-0.13

POSITIVE LOGITS

asma

0.15

usta

0.15

allery

0.15

isk

0.14

ÑĢÐ¾Ñĩ

0.14

qt

0.14

caf

0.14

 Bowman

0.14

å°ģ

0.14

DAL

0.14

Activations Density 0.005%

key terms related to media coverage and statistics

No Comments

No Known Activations