INDEX

Explanations

instances of capitalization, likely focusing on proper nouns or significant terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

nen

-0.19

li

-0.18

nes

-0.17

nees

-0.17

ss

-0.17

lo

-0.17

rd

-0.17

º

-0.17

rome

-0.16

loe

-0.15

POSITIVE LOGITS

izabeth

0.17

SCO

0.16

Åĳs

0.15

ichel

0.15

-disable

0.15

Ãłnh

0.15

/disable

0.15

erald

0.14

zzo

0.14

enis

0.14

Activations Density 0.147%

instances of capitalization, likely focusing on proper nouns or significant terms

No Comments

No Known Activations