INDEX

Explanations

references to personal ownership or possessive language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

edn

-0.17

Lip

-0.15

 reven

-0.15

ATAL

-0.15

 Platt

-0.14

orns

-0.14

Intent

-0.14

á»Ľt

-0.13

asca

-0.13

iban

-0.13

POSITIVE LOGITS

age

0.18

ãĤº

0.17

ovol

0.15

estic

0.15

oslav

0.15

 Jerseys

0.14

 quarter

0.14

mono

0.14

åĽº

0.14

mage

0.14

Activations Density 0.035%

references to personal ownership or possessive language

No Comments

No Known Activations