© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58893
    Prev
    Next
    INDEX
    Explanations

    attract

    np_max-act · gemini-2.0-flash

    The neuron activates on any token containing the character sequence “tract” (e.g. attract, attractor, attraction).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moments
    -0.08
    Jud
    -0.08
     Med
    -0.06
    Cmd
    -0.06
     minutos
    -0.06
    _Work
    -0.06
    ideo
    -0.06
    Pages
    -0.06
     commande
    -0.06
    _End
    -0.06
    POSITIVE LOGITS
     attracted
    0.14
     attract
    0.13
     attracting
    0.12
     attractive
    0.10
     attracts
    0.10
     attraction
    0.10
     attractiveness
    0.08
     ATTR
    0.07
    屬
    0.07
    ัก
    0.07
    Activations Density 0.015%

    No Known Activations