INDEX

Explanations

references to events held at the White House

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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°ÑĤÐ°ÑĢ

-0.18

Éµ

-0.15

mai

-0.15

dorf

-0.14

omer

-0.14

 Sanctuary

-0.14

/community

-0.14

Ð¸Ð½Ñĭ

-0.13

alet

-0.13

atro

-0.13

POSITIVE LOGITS

 White

0.34

White

0.28

 Oval

0.28

 WHITE

0.24

 Blair

0.23

 Executive

0.23

 Cabinet

0.21

 Situation

0.21

 Marine

0.21

WHITE

0.21

Activations Density 0.087%

references to events held at the White House

No Comments

No Known Activations