INDEX

Explanations

elements of programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

etto

-0.17

aku

-0.15

elen

-0.15

tank

-0.15

ao

-0.14

ISIBLE

-0.14

_firestore

-0.14

æĹıèĩªæ²»

-0.13

[].

-0.13

igit

-0.13

POSITIVE LOGITS

(:,

0.28

(:

0.22

(:

0.21

(end

0.20

0.19

 Vend

0.18

end

0.18

 Logical

0.18

(strcmp

0.17

Activations Density 0.008%

elements of programming code

No Comments

No Known Activations