INDEX

Explanations

code structure and function definitions in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

\grid

-0.21

stery

-0.19

ripp

-0.18

 STAR

-0.17

âĺħâĺħ

-0.17

astery

-0.16

krv

-0.15

=*/

-0.15

STAR

-0.15

undi

-0.15

POSITIVE LOGITS

0.52

0.36

**

0.25

*"

0.21

 *↵

0.19

*_

0.18

 *↵↵

0.16

 *----------------------------------------------------------------

0.15

.*

0.15

 *č↵

0.15

Activations Density 0.049%

code structure and function definitions in programming contexts

No Comments

No Known Activations