INDEX

Explanations

references to the name "Leo" or associated individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

jian

-0.16

uguay

-0.15

Ngh

-0.14

ALER

-0.14

zhou

-0.14

beit

-0.14

ManagedObject

-0.14

lease

-0.14

aleb

-0.14

ìĤ

-0.14

POSITIVE LOGITS

 Lion

0.17

chas

0.17

Ã¬n

0.16

otos

0.16

 Messi

0.15

à¸Ĺà¸£

0.15

 Bloom

0.15

egasus

0.15

onto

0.14

sett

0.14

Activations Density 0.015%

references to the name "Leo" or associated individuals

No Comments

No Known Activations