INDEX

Explanations

instructions related to planning and making reservations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

uctose

-0.17

 Nach

-0.15

ecided

-0.15

ivol

-0.14

sov

-0.14

arp

-0.14

apid

-0.14

lovak

-0.14

kov

-0.14

lok

-0.14

POSITIVE LOGITS

 early

0.21

æĹ©

0.19

early

0.17

 earlier

0.16

 Early

0.16

 Amend

0.16

 Lead

0.15

 lead

0.15

Early

0.15

çĩ

0.15

Activations Density 0.078%

instructions related to planning and making reservations

No Comments

No Known Activations