INDEX

Explanations

programming-related syntax, particularly focusing on TypeScript or interface definitions

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

lore

-0.15

bel

-0.14

åĩĮ

-0.14

pul

-0.13

[](

-0.13

umpt

-0.13

UNG

-0.13

 proprio

-0.13

warts

-0.13

wald

-0.13

POSITIVE LOGITS

 string

0.30

 boolean

0.26

string

0.24

 number

0.23

any

0.23

boolean

0.22

 typeof

0.22

 Partial

0.21

 Pick

0.21

any

0.21

Activations Density 0.008%

programming-related syntax, particularly focusing on TypeScript or interface definitions

No Comments

No Known Activations