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. 7-RESID-POST-AA
    6. 128804
    Prev
    Next
    INDEX
    Explanations

    .

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     handshake
    -0.07
     mesure
    -0.07
     setPassword
    -0.07
     Number
    -0.06
     Ov
    -0.06
     Pedido
    -0.06
     Ranked
    -0.06
     proxy
    -0.06
    _plugin
    -0.06
     Helm
    -0.06
    POSITIVE LOGITS
    -create
    0.06
    ableOpacity
    0.06
    ethoven
    0.06
    ゙゙
    0.06
    IIIK
    0.06
    สะ
    0.06
    utar
    0.06
     Would
    0.06
    upil
    0.06
    _REPLY
    0.06
    Activations Density 0.010%

    No Known Activations