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. 30432
    Prev
    Next
    INDEX
    Explanations

    Events

    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
    žen
    -0.07
    ★★
    -0.07
     vyšší
    -0.06
     uží
    -0.06
    OfSize
    -0.06
    iete
    -0.06
    Gem
    -0.06
     trấn
    -0.06
    Seq
    -0.06
    logen
    -0.06
    POSITIVE LOGITS
     drilling
    0.07
    ://%
    0.06
    iễn
    0.06
     skype
    0.06
     expenditures
    0.06
     drives
    0.06
     Dost
    0.06
    -driven
    0.06
     companions
    0.06
     divers
    0.06
    Activations Density 0.000%

    No Known Activations