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. 113086
    Prev
    Next
    INDEX
    Explanations

    CCD

    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
     мон
    -0.08
    	Port
    -0.07
     Fet
    -0.07
     пар
    -0.07
    (agent
    -0.07
    aremos
    -0.07
    .OutputStream
    -0.06
    وروب
    -0.06
     dias
    -0.06
    (cors
    -0.06
    POSITIVE LOGITS
     CCD
    0.13
    CD
    0.07
    مدة
    0.07
    ccc
    0.06
    ldata
    0.06
     kb
    0.06
    idea
    0.06
     upstairs
    0.06
    facility
    0.06
     skulls
    0.06
    Activations Density 0.001%

    No Known Activations