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. 125159
    Prev
    Next
    INDEX
    Explanations

    cure

    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
     Boyd
    -0.07
     Bett
    -0.07
     yerini
    -0.07
     Mitt
    -0.07
     Oakland
    -0.07
    شاه
    -0.06
    尊
    -0.06
     vestib
    -0.06
     Üst
    -0.06
     LSB
    -0.06
    POSITIVE LOGITS
     cure
    0.17
     curing
    0.15
     Cure
    0.14
     cured
    0.14
    ure
    0.11
     remedy
    0.08
    URE
    0.08
    UR
    0.07
     lure
    0.07
    928
    0.07
    Activations Density 0.004%

    No Known Activations