INDEX

Explanations

references to Facebook and its associated features or links

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

istic

-0.16

ãĥ©ãĥĥãĤ¯

-0.15

exact

-0.15

ÑħÐ¸

-0.15

 Richardson

-0.15

agli

-0.14

vetica

-0.14

'Brien

-0.14

ê¹

-0.14

omor

-0.14

POSITIVE LOGITS

 Messenger

0.23

/twitter

0.21

(fb

0.20

0.19

/T

0.19

 messenger

0.18

fb

0.18

.com

0.17

istan

0.17

FB

0.17

Activations Density 0.011%

references to Facebook and its associated features or links

No Comments

No Known Activations