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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 29476
    Prev
    Next
    INDEX
    Explanations

    datetime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    وح
    -0.07
     bourgeois
    -0.06
    increment
    -0.06
     erb
    -0.06
    uced
    -0.06
    slope
    -0.06
     Reds
    -0.06
    、お
    -0.06
     weight
    -0.06
     bike
    -0.06
    POSITIVE LOGITS
     dateTime
    0.09
    _datetime
    0.08
    [Math
    0.07
     zároveň
    0.07
    のみ
    0.07
     Authenticate
    0.07
    _dma
    0.07
    νει
    0.07
    DECLARE
    0.07
     přím
    0.07
    Activations Density 0.008%

    No Known Activations