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. 19-RESID-POST-AA
    6. 59687
    Prev
    Next
    INDEX
    Explanations

    Fig

    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
    лено
    -0.07
    ether
    -0.07
    ância
    -0.07
    нути
    -0.07
     OMIT
    -0.06
     containment
    -0.06
    Vien
    -0.06
     datum
    -0.06
    .metadata
    -0.06
     Applications
    -0.06
    POSITIVE LOGITS
    (rep
    0.07
     Mädchen
    0.07
     За
    0.07
    (job
    0.06
    (renderer
    0.06
     //------------------------------------------------
    0.06
    .While
    0.06
     shock
    0.06
     갈
    0.06
     blows
    0.06
    Activations Density 0.001%

    No Known Activations