Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 122616
    Prev
    Next
    INDEX
    Explanations

    extinguish

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TextField
    -0.07
     Bản
    -0.07
     ICollection
    -0.06
    _summary
    -0.06
     الاع
    -0.06
    okrat
    -0.06
    InputElement
    -0.06
     cruise
    -0.06
     jiné
    -0.06
     begins
    -0.06
    POSITIVE LOGITS
     extingu
    0.17
     extinct
    0.10
    滅
    0.07
    灭
    0.07
     sentient
    0.07
     queryString
    0.06
     ambulance
    0.06
     Şimdi
    0.06
    (Line
    0.06
     kor
    0.06
    Activations Density 0.010%

    No Known Activations