© 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. 19-RESID-POST-AA
    6. 28248
    Prev
    Next
    INDEX
    Explanations

    Excel VBA code

    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
     عليك
    -0.06
    EFI
    -0.06
     Compensation
    -0.06
     Latitude
    -0.06
     真
    -0.06
     H
    -0.06
     каз
    -0.06
    'H
    -0.06
    اسطة
    -0.06
    ΜΑ
    -0.06
    POSITIVE LOGITS
    ointment
    0.07
    acket
    0.07
    =output
    0.06
     editable
    0.06
     listing
    0.06
    elper
    0.06
    Risk
    0.06
     Atom
    0.06
    .GET
    0.06
     lent
    0.06
    Activations Density 0.010%

    No Known Activations