INDEX

Explanations

ordinal numbers and references to annual events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

±

-0.15

 lá»Ĺ

-0.14

cess

-0.14

zÃ¡

-0.14

æ´

-0.14

Blank

-0.14

alous

-0.14

æ§ĺ

-0.14

enia

-0.13

.createClass

-0.13

POSITIVE LOGITS

ãĥ¬ãĥ¼

0.16

iske

0.15

igar

0.14

uze

0.14

antro

0.14

ungle

0.14

iman

0.14

IPC

0.14

SEQ

0.14

Activations Density 0.029%

ordinal numbers and references to annual events

No Comments

No Known Activations