INDEX

Explanations

phrases related to permanence and positive outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

é¬¼

-0.16

ç¦®

-0.16

oft

-0.16

ç¤¼

-0.15

inions

-0.14

 prov

-0.14

eil

-0.14

ador

-0.14

 newline

-0.13

Ø³Ø±

-0.13

POSITIVE LOGITS

permanent

0.16

 permanently

0.16

 permanent

0.16

altung

0.16

ushima

0.15

igung

0.15

(;;

0.15

iche

0.15

æ°¸ä¹ħ

0.15

 Forever

0.14

Activations Density 0.194%

phrases related to permanence and positive outcomes

No Comments

No Known Activations