INDEX

Explanations

programming constructs and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

.scalablytyped

-0.17

Ãłng

-0.16

 Principal

-0.15

Laz

-0.15

âĢİ

-0.15

 Principle

-0.15

idge

-0.14

 ÐľÑĸÐ½ÑĸÑģÑĤ

-0.14

Ð¾Ð·Ð°

-0.14

Ø³ØªØ±

-0.14

POSITIVE LOGITS

 both

0.28

both

0.28

Both

0.25

 BOTH

0.25

 Both

0.24

 neither

0.22

_both

0.21

Neither

0.20

 beiden

0.20

 Neither

0.19

Activations Density 0.175%

programming constructs and data structures

No Comments

No Known Activations