INDEX

Explanations

terms related to seating and positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

itational

-0.15

osed

-0.14

alt

-0.14

oeff

-0.14

isk

-0.14

 Victim

-0.14

enheim

-0.14

egin

-0.14

feld

-0.14

ORIZ

-0.14

POSITIVE LOGITS

å¸Ń

0.21

manship

0.21

-seat

0.19

lift

0.18

æ¤ħ

0.17

ellite

0.17

åº§

0.17

 seat

0.16

ellites

0.16

 seats

0.15

Activations Density 0.043%

terms related to seating and positions

No Comments

No Known Activations