INDEX

Explanations

phrases indicating primary factors or main reasons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Interpreter

-0.14

ernote

-0.14

TRA

-0.14

ÑĤÐ°Ð¶

-0.14

ÐµÐ³Ð¾ÑĢ

-0.14

intel

-0.13

hlas

-0.13

 Ð±Ð°Ð½ÐºÑĥ

-0.13

cel

-0.13

.printStackTrace

-0.13

POSITIVE LOGITS

 common

0.22

 thing

0.21

 things

0.21

 most

0.18

thing

0.18

 commonly

0.17

 ninja

0.17

 ways

0.16

Thing

0.15

 chief

0.15

Activations Density 0.093%

phrases indicating primary factors or main reasons

No Comments

No Known Activations