INDEX

Explanations

programming-related syntax and function calls

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

uce

-0.17

inge

-0.15

onom

-0.15

(argument

-0.14

ture

-0.14

OLER

-0.14

ãģ¾ãģ¨

-0.14

oler

-0.14

iffer

-0.14

aldi

-0.14

POSITIVE LOGITS

img

0.35

(img

0.30

img

0.29

=img

0.29

obj

0.28

/img

0.27

img

0.27

 addr

0.26

.img

0.25

-img

0.24

Activations Density 0.222%

programming-related syntax and function calls

No Comments

No Known Activations