INDEX

Explanations

technical terms related to software development and programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

RLF

-0.15

é»

-0.13

alu

-0.13

appen

-0.13

 Destructor

-0.13

dar

-0.13

ÑĬ

-0.13

/animate

-0.13

 tact

-0.12

 Fetish

-0.12

POSITIVE LOGITS

 running

0.34

 written

0.26

running

0.26

 developed

0.23

 supporting

0.22

 Running

0.22

 powering

0.21

 RUNNING

0.20

 shipping

0.20

(__

0.20

Activations Density 0.473%

technical terms related to software development and programming languages

No Comments

No Known Activations