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. 112645
    Prev
    Next
    INDEX
    Explanations

    For/Per

    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
    若
    -0.07
    (route
    -0.07
    license
    -0.07
    Factors
    -0.06
     QWidget
    -0.06
    \Backend
    -0.06
    _CHANNELS
    -0.06
    阳城
    -0.06
    ān
    -0.06
     текст
    -0.06
    POSITIVE LOGITS
     champ
    0.07
     terör
    0.07
     shalt
    0.06
     відпов
    0.06
     Spin
    0.06
     doğr
    0.06
     smell
    0.06
     coop
    0.06
     gü
    0.06
     التش
    0.06
    Activations Density 0.060%

    No Known Activations