INDEX

Explanations

elements that provide insights and reflections on various topics or narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

è¯ī

-0.16

mock

-0.15

 Invent

-0.15

ption

-0.14

 ?>"/>↵

-0.14

åİļ

-0.14

è¯´æĺİ

-0.14

(fullfile

-0.14

ipl

-0.13

tempts

-0.13

POSITIVE LOGITS

nug

0.35

tid

0.34

 gems

0.33

 observations

0.32

 insights

0.30

 pearls

0.29

observations

0.28

 Gems

0.27

 insight

0.26

 pearl

0.26

Activations Density 0.209%

elements that provide insights and reflections on various topics or narratives

No Comments

No Known Activations