INDEX

Explanations

references to personal experiences or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

esz

-0.15

.apiUrl

-0.14

aroo

-0.14

bak

-0.14

jom

-0.13

emia

-0.13

ew

-0.13

.defaultProps

-0.13

edis

-0.13

ayer

-0.13

POSITIVE LOGITS

 personal

0.21

/person

0.17

PGA

0.17

 Personal

0.16

personal

0.16

istic

0.16

LEE

0.16

Personal

0.15

-uppercase

0.15

Î¯Î´Î±

0.15

Activations Density 0.025%

references to personal experiences or attributes

No Comments

No Known Activations