INDEX

Explanations

references to requests for information and governmental transparency

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

olatile

-0.15

èĦ

-0.14

nez

-0.14

cep

-0.14

ç²

-0.14

oland

-0.14

 gent

-0.13

åħ·

-0.13

offer

-0.13

ÏĢÎ¿ÏĤ

-0.13

POSITIVE LOGITS

FO

0.42

 Freedom

0.36

Freedom

0.31

FO

0.30

 freedom

0.26

 records

0.24

 Records

0.23

 requester

0.23

fo

0.23

Fo

0.23

Activations Density 0.031%

references to requests for information and governmental transparency

No Comments

No Known Activations