INDEX

Explanations

specific year numbers

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

hausen

-0.17

åĪ¸

-0.16

ided

-0.16

undy

-0.15

OwnProperty

-0.14

beer

-0.13

asse

-0.13

oleÄį

-0.13

osate

-0.13

Ã¤ter

-0.13

POSITIVE LOGITS

ovel

0.17

flies

0.16

Lap

0.15

 Coloring

0.15

 Burl

0.15

.TryParse

0.15

alcon

0.14

ÑĹ

0.14

\Configuration

0.14

uns

0.13

Activations Density 0.026%

specific year numbers

No Comments

No Known Activations