INDEX

Explanations

specific architectural and design features of buildings or objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 èĸ

-0.14

ednou

-0.14

hop

-0.14

aN

-0.14

Ä±rak

-0.14

ady

-0.14

 nastav

-0.13

 Cush

-0.13

koli

-0.13

RAINT

-0.13

POSITIVE LOGITS

-style

0.17

aeda

0.17

ized

0.16

å¼ı

0.15

 style

0.14

-esque

0.14

style

0.14

-equipped

0.14

acco

0.14

inue

0.13

Activations Density 0.176%

specific architectural and design features of buildings or objects

No Comments

No Known Activations

specific architectural and design features of buildings or objects

No Comments

No Known Activations