© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 27598
    Prev
    Next
    INDEX
    Explanations

    know

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inclusion
    -0.06
    .neg
    -0.06
     "\(
    -0.06
    _journal
    -0.06
    ateg
    -0.06
    materials
    -0.06
    _tran
    -0.05
    .normalize
    -0.05
    jejer
    -0.05
    etermined
    -0.05
    POSITIVE LOGITS
    bout
    0.07
    ينا
    0.07
     evident
    0.07
     Off
    0.07
     chopping
    0.06
    !↵↵
    0.06
    vert
    0.06
    Report
    0.06
     acceptable
    0.06
     ssl
    0.06
    Activations Density 0.011%

    No Known Activations