INDEX

Explanations

expressions related to complexity and simple truths

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

obia

-0.17

 skeleton

-0.16

olec

-0.16

Tomorrow

-0.15

 Tomorrow

-0.15

 Today

-0.14

 Skeleton

-0.14

ib

-0.14

atts

-0.14

dit

-0.14

POSITIVE LOGITS

 actually

0.32

actually

0.30

 aslÄ±nda

0.29

åħ¶å®ŀ

0.28

tb

0.28

 really

0.26

Actually

0.25

 vlastnÄĽ

0.25

 Actually

0.24

 eigentlich

0.23

Activations Density 0.408%

expressions related to complexity and simple truths

No Comments

No Known Activations