© 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
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 54328
    Prev
    Next
    INDEX
    Explanations

    common English words

    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
     lyrics
    -0.06
    .physics
    -0.06
    도가
    -0.06
    _comp
    -0.06
    子供
    -0.06
    guess
    -0.06
    Does
    -0.06
    еси
    -0.06
     Summers
    -0.06
     myster
    -0.06
    POSITIVE LOGITS
     maternity
    0.07
     onUpdate
    0.07
     MN
    0.06
     phiếu
    0.06
    gency
    0.06
    _pdu
    0.06
     flag
    0.06
     filib
    0.06
    esan
    0.06
     routine
    0.06
    Activations Density 0.045%

    No Known Activations