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. 3-RESID-POST-AA
    6. 94289
    Prev
    Next
    INDEX
    Explanations

    dates or relationships

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ضد
    -0.06
    atus
    -0.06
    .internal
    -0.06
     connectors
    -0.06
    agree
    -0.06
     defendant
    -0.06
    _parameters
    -0.06
    (ByVal
    -0.06
     vehicles
    -0.06
     connector
    -0.06
    POSITIVE LOGITS
     klient
    0.08
    Military
    0.07
     nhé
    0.07
     důležité
    0.07
     DELETE
    0.06
    <>();↵
    0.06
    Denver
    0.06
    Html
    0.06
     Wanted
    0.06
    311
    0.06
    Activations Density 0.298%

    No Known Activations