INDEX

Explanations

key terms associated with performance and ownership in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

agher

-0.17

aea

-0.16

 Weaver

-0.15

hn

-0.15

asio

-0.14

 block

-0.14

.Me

-0.14

MES

-0.14

cko

-0.14

SKI

-0.14

POSITIVE LOGITS

oling

0.15

quiv

0.15

aban

0.15

infeld

0.15

uke

0.15

èĩªæĭį

0.14

BOR

0.14

ulfill

0.14

Bor

0.14

 divis

0.13

Activations Density 0.002%

key terms associated with performance and ownership in various contexts

No Comments

No Known Activations