INDEX

Explanations

technical terms and concepts related to computer programming and assembly language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

fsp

-0.16

zon

-0.15

anon

-0.15

 Dillon

-0.15

-0.14

.getLocal

-0.14

à¥°

-0.14

ell

-0.14

bomb

-0.13

POSITIVE LOGITS

Bus

0.19

bus

0.18

bus

0.17

 latch

0.16

Bus

0.16

.Bus

0.16

 register

0.15

å¯Ħ

0.15

_bus

0.15

greg

0.14

Activations Density 0.043%

technical terms and concepts related to computer programming and assembly language

No Comments

No Known Activations