INDEX

Explanations

references to honors, awards, and recognitions received by individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

istrat

-0.15

azor

-0.15

istributed

-0.15

èĪĪ

-0.14

PK

-0.14

ANT

-0.14

Assistant

-0.14

ÏģÎ¹Ïĥ

-0.13

amera

-0.13

AndPassword

-0.13

POSITIVE LOGITS

 Lifetime

0.35

 lifetime

0.33

Lifetime

0.31

 Doctor

0.27

lifetime

0.26

 doctor

0.25

 Order

0.24

Doctor

0.23

 decoration

0.23

 Knight

0.23

Activations Density 0.085%

references to honors, awards, and recognitions received by individuals

No Comments

No Known Activations