INDEX

Explanations

programming symbols and mathematical expressions

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

 zero

-0.21

 Zero

-0.20

zer

-0.18

zer

-0.18

 zeros

-0.16

culo

-0.16

nil

-0.16

-zero

-0.16

 Null

-0.16

benh

-0.15

POSITIVE LOGITS

ews

0.17

cape

0.15

ensch

0.15

IENT

0.15

ITTER

0.15

apiro

0.14

enne

0.14

 vice

0.14

BST

0.14

kbd

0.13

Activations Density 0.104%

programming symbols and mathematical expressions

No Comments

No Known Activations