INDEX

Explanations

mathematical variables and their relationships in expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

_{

-0.26

-0.25

_{

-0.22

_$

-0.18

$_

-0.17

âĤģ

-0.16

_\

-0.16

 latter

-0.16

stacle

-0.15

udy

-0.15

POSITIVE LOGITS

^K

0.18

^\

0.16

0.15

apper

0.15

^-

0.15

{}_

0.15

 Anders

0.14

ialis

0.14

.datatables

0.14

Activations Density 0.132%

mathematical variables and their relationships in expressions

No Comments

No Known Activations