INDEX

Explanations

abbreviations or acronyms related to organizations and their projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

oose

-0.16

elem

-0.15

ampion

-0.14

pit

-0.14

oft

-0.14

EPS

-0.14

erno

-0.14

áº§m

-0.14

uml

-0.14

UCKET

-0.13

POSITIVE LOGITS

mapper

0.17

fried

0.16

anzeigen

0.15

rane

0.14

ardin

0.14

linky

0.14

otec

0.14

/runtime

0.14

ewise

0.13

chooser

0.13

Activations Density 0.488%

abbreviations or acronyms related to organizations and their projects

No Comments

No Known Activations