© 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. 19-RESID-POST-AA
    6. 29364
    Prev
    Next
    INDEX
    Explanations

    into

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ANTITY
    -0.07
     ورود
    -0.06
    “.
    -0.06
    setBackground
    -0.06
    cities
    -0.06
    /tags
    -0.06
     svo
    -0.06
     ortadan
    -0.05
       		
    -0.05
    ीछ
    -0.05
    POSITIVE LOGITS
     κατα
    0.07
    _Inter
    0.07
     Merc
    0.07
    ounsel
    0.07
     commenced
    0.07
     Breast
    0.07
     documented
    0.06
    icio
    0.06
    filename
    0.06
    butt
    0.06
    Activations Density 0.010%

    No Known Activations