INDEX

Explanations

references to organizational structures and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

oust

-0.15

ieres

-0.14

iero

-0.14

enek

-0.14

udes

-0.14

 structural

-0.13

kok

-0.13

venes

-0.13

sonian

-0.13

ENE

-0.13

POSITIVE LOGITS

 individuals

0.18

 society

0.17

 individual

0.17

individual

0.17

 Individual

0.16

 Individuals

0.15

 indiv

0.14

 precinct

0.14

Individual

0.14

emble

0.14

Activations Density 0.325%

references to organizational structures and relationships

No Comments

No Known Activations