INDEX

Explanations

references to organizations or authorities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

iffin

-0.16

ald

-0.15

ahan

-0.15

alis

-0.14

 Gust

-0.14

.AddRange

-0.14

ihu

-0.14

Î¹ÎºÎ¿

-0.14

oons

-0.14

istrar

-0.14

POSITIVE LOGITS

VO

0.22

vo

0.20

VO

0.19

_VO

0.18

 anchor

0.17

FILE

0.16

 colorful

0.16

Vo

0.16

 listener

0.15

abbage

0.15

Activations Density 0.008%

references to organizations or authorities

No Comments

No Known Activations