INDEX

Explanations

abbreviations or initials of individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

DDS

-0.16

unch

-0.15

anio

-0.15

immel

-0.15

 thá»§

-0.14

ANNEL

-0.14

Cyc

-0.14

Äįan

-0.14

leon

-0.14

anja

-0.13

POSITIVE LOGITS

hots

0.16

Mismatch

0.14

 Mour

0.14

rita

0.14

Ã¡nh

0.13

 Wade

0.13

esson

0.13

 Sour

0.13

inery

0.13

ÏĥÏĥ

0.13

Activations Density 0.047%

abbreviations or initials of individuals and organizations

No Comments

No Known Activations