INDEX

Explanations

punctuation and other formatting elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

uco

-0.16

.pixel

-0.15

Ã¸y

-0.15

à¸±à¸¢

-0.15

>(_

-0.15

oter

-0.14

ahlen

-0.14

enas

-0.14

zan

-0.14

Checker

-0.14

POSITIVE LOGITS

 latest

0.19

Showing

0.17

 Latest

0.17

Latest

0.15

rax

0.15

til

0.15

 newest

0.15

 below

0.15

sus

0.14

Below

0.14

Activations Density 0.079%

punctuation and other formatting elements

No Comments

No Known Activations