INDEX

Explanations

programming and coding syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 irre

-0.15

Hi

-0.15

 Northern

-0.15

ris

-0.14

 éĿ

-0.14

.getContext

-0.14

INGTON

-0.14

Hex

-0.14

 Polar

-0.14

 Jacqu

-0.13

POSITIVE LOGITS

CI

0.21

CI

0.21

 Malaysia

0.20

Ø§ÙĬØ§

0.19

 Malays

0.19

flashdata

0.19

addtogroup

0.18

 hooks

0.18

 userdata

0.18

 Kuala

0.18

Activations Density 0.003%

programming and coding syntax

No Comments

No Known Activations