INDEX

Explanations

technical references to programming concepts and frameworks

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

mij

-0.15

 laps

-0.15

egen

-0.15

 Shepard

-0.14

adt

-0.14

/AFP

-0.14

tun

-0.14

ÏģÎ®

-0.14

 prive

-0.13

ollipop

-0.13

POSITIVE LOGITS

 spring

0.42

 Spring

0.41

spring

0.39

Spring

0.36

 Springs

0.30

	Spring

0.29

.Spring

0.29

 SpringApplication

0.28

 springs

0.27

(Spring

0.27

Activations Density 0.056%

technical references to programming concepts and frameworks

No Comments

No Known Activations