INDEX

Explanations

references to significant locations related to the White House and its historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Ð°ÑĤÐ¾Ðº

-0.17

roje

-0.15

ilm

-0.15

eam

-0.15

ToPoint

-0.15

ooth

-0.15

rogen

-0.14

croft

-0.14

atz

-0.14

zhou

-0.14

POSITIVE LOGITS

 White

0.44

White

0.37

 WHITE

0.30

.White

0.28

 white

0.27

.white

0.25

WHITE

0.25

-white

0.23

_white

0.23

 Oval

0.23

Activations Density 0.105%

references to significant locations related to the White House and its historical context

No Comments

No Known Activations