INDEX

Explanations

elements related to achievement and milestones 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 @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Nose

-0.16

aber

-0.16

ula

-0.15

amel

-0.15

ãĥ¼ãĥł

-0.15

oca

-0.14

ÛĮÙħÛĮ

-0.14

à¸£à¸ĵ

-0.14

eros

-0.14

 noses

-0.14

POSITIVE LOGITS

 previously

0.18

uzzi

0.16

 finally

0.15

æŃ´

0.15

tings

0.15

vido

0.15

ophobic

0.15

ActionCreators

0.14

 previous

0.14

ingo

0.14

Activations Density 0.255%

elements related to achievement and milestones in various contexts

No Comments

No Known Activations