INDEX

Explanations

product names and brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 plain

-0.14

 pearl

-0.14

 Horizon

-0.14

 Treasure

-0.14

ussy

-0.14

Mocks

-0.14

_plain

-0.14

izzling

-0.13

ãģĪãģŁ

-0.13

POSITIVE LOGITS

Pro

0.20

pro

0.19

(PR

0.18

.Pro

0.17

Pru

0.17

olec

0.17

-Pro

0.16

opro

0.16

Pro

0.16

/pro

0.16

Activations Density 0.123%

product names and brands

No Comments

No Known Activations