INDEX

Explanations

programming-related syntax elements and annotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 over

-0.25

Over

-0.19

 Over

-0.18

over

-0.18

 OVER

-0.17

-over

-0.16

obre

-0.16

zsche

-0.16

 sobre

-0.15

otte

-0.14

POSITIVE LOGITS

åĢ«

0.15

ê¸ī

0.15

 private

0.15

emoc

0.15

Ñĥ

0.14

alaxy

0.14

Ø§Ø¬Ø±

0.14

gp

0.14

alis

0.14

Activations Density 0.012%

programming-related syntax elements and annotations

No Comments

No Known Activations