INDEX

Explanations

parentheses and their corresponding structure in documents

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

xaf

-0.21

 McDon

-0.17

ucus

-0.16

 needles

-0.14

 pride

-0.14

osy

-0.14

ohn

-0.14

aption

-0.13

plusplus

-0.13

Ð½Ð°ÑĤ

-0.13

POSITIVE LOGITS

ritch

0.17

TestFixture

0.14

-des

0.14

çĤ

0.14

REFERRED

0.14

obook

0.14

yz

0.14

VK

0.13

bara

0.13

PM

0.13

Activations Density 0.391%

parentheses and their corresponding structure in documents

No Comments

No Known Activations