INDEX

Explanations

references to trips and travel-related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 punct

-0.17

ReadWrite

-0.15

metics

-0.15

anou

-0.14

 Spear

-0.14

enheim

-0.14

ENDOR

-0.14

OUNDS

-0.14

entai

-0.14

 Commonwealth

-0.14

POSITIVE LOGITS

izzo

0.17

Ľ°

0.15

qua

0.15

atre

0.14

ä¸ģ

0.14

GAN

0.14

BSD

0.14

undry

0.14

 interfer

0.13

 Barack

0.13

Activations Density 0.016%

references to trips and travel-related activities

No Comments

No Known Activations