INDEX

Explanations

specific pronouns and related terms indicating active participants or stakeholders in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 everywhere

-0.17

yet

-0.16

 anywhere

-0.15

ANY

-0.15

LOS

-0.15

nty

-0.14

Anywhere

-0.14

 eventually

-0.14

ÐµÑī

-0.14

 Cunningham

-0.14

POSITIVE LOGITS

 each

0.26

each

0.25

 Each

0.22

Each

0.20

 cada

0.20

à¹Īà¸¥à¸°

0.20

 individual

0.20

.each

0.19

 EACH

0.19

_each

0.18

Activations Density 0.008%

specific pronouns and related terms indicating active participants or stakeholders in a context

No Comments

No Known Activations