INDEX

Explanations

references to the word "beacon" and its variations

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

ÄĲT

-0.15

grave

-0.15

kova

-0.15

vere

-0.15

olvers

-0.14

arb

-0.14

inka

-0.14

icus

-0.14

zens

-0.14

ä¿Ĺ

-0.14

POSITIVE LOGITS

 Mane

0.16

à¤¨à¤²

0.15

~>

0.15

semb

0.15

iche

0.15

adar

0.14

issan

0.14

lope

0.14

rist

0.14

Activations Density 0.003%

references to the word "beacon" and its variations

No Comments

No Known Activations