Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 24083
    Prev
    Next
    INDEX
    Explanations

    scientific modeling

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _bounds
    -0.06
     Bad
    -0.06
     fools
    -0.06
     Going
    -0.06
     Ram
    -0.06
    irá
    -0.06
     Control
    -0.06
    ForObject
    -0.06
     going
    -0.06
    nt
    -0.06
    POSITIVE LOGITS
     elektr
    0.06
     Шев
    0.06
    	CString
    0.06
    _Zero
    0.06
    ,LOCATION
    0.06
    ODB
    0.06
    แบบ
    0.06
    .descripcion
    0.06
     Inventory
    0.06
     zakáz
    0.06
    Activations Density 0.169%

    No Known Activations