© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 115393
    Prev
    Next
    INDEX
    Explanations

    safety

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     politique
    -0.07
     Angebot
    -0.06
     elektrik
    -0.06
    ců
    -0.06
     detal
    -0.06
     TCHAR
    -0.06
    Fal
    -0.06
     Registered
    -0.06
     sólo
    -0.06
    rhs
    -0.06
    POSITIVE LOGITS
    _self
    0.07
    DebugEnabled
    0.06
    CustomAttributes
    0.06
     가장
    0.06
    MASConstraintMaker
    0.06
     PropertyChanged
    0.06
    .getSelectionModel
    0.06
    ह
    0.06
     γ
    0.06
    ardır
    0.06
    Activations Density 0.027%

    No Known Activations