INDEX

Explanations

HTML tags and navigation elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ÑĩÐ¸Ð½

-0.16

 @"↵

-0.15

aina

-0.14

åĲĪãĤıãģĽ

-0.14

/buttons

-0.14

/Table

-0.14

plen

-0.14

uran

-0.14

AGMA

-0.14

ENA

-0.14

POSITIVE LOGITS

li

0.43

li

0.39

<li

0.34

Li

0.30

_li

0.28

.li

0.28

Li

0.28

-li

0.28

/li

0.27

LI

0.26

Activations Density 0.031%

HTML tags and navigation elements

No Comments

No Known Activations