INDEX

Explanations

technical terms related to software programming

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

/stdc

-0.18

icut

-0.16

 Pell

-0.15

/ws

-0.14

 shutter

-0.14

gars

-0.14

ega

-0.14

eki

-0.14

.wik

-0.14

 burn

-0.14

POSITIVE LOGITS

 spin

0.24

 atomic

0.22

 Spin

0.21

spin

0.20

dev

0.19

 struct

0.19

 Atomic

0.19

EXPORT

0.19

GFP

0.18

Spin

0.18

Activations Density 0.009%

technical terms related to software programming

No Comments

No Known Activations