INDEX

Explanations

references to individuals holding the title of "President" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ings

-0.19

ibr

-0.15

orca

-0.15

ëį°

-0.15

eras

-0.14

lore

-0.14

isay

-0.14

ivan

-0.14

ãģĸ

-0.14

POSITIVE LOGITS

ially

0.28

IAL

0.24

-elect

0.21

ials

0.20

elect

0.20

 Obama

0.19

ential

0.18

/operators

0.17

Ð¸Ð´ÐµÐ½ÑĤÐ°

0.17

 Barack

0.17

Activations Density 0.047%

references to individuals holding the title of "President" in various contexts

No Comments

No Known Activations