© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 91279
    Prev
    Next
    INDEX
    Explanations

    colon

    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
    ánh
    -0.08
     الهند
    -0.07
     директор
    -0.06
    یزی
    -0.06
    Weekly
    -0.06
    GitHub
    -0.06
    .num
    -0.06
    Dod
    -0.06
     Madame
    -0.06
    Ì
    -0.06
    POSITIVE LOGITS
    elivery
    0.06
     WC
    0.06
     gst
    0.06
     RESULT
    0.06
    ộn
    0.06
    WP
    0.06
     Transformation
    0.06
     Crown
    0.06
    _FREQUENCY
    0.06
     conversation
    0.06
    Activations Density 0.006%

    No Known Activations