© 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. 15-RESID-POST-AA
    6. 89763
    Prev
    Next
    INDEX
    Explanations

    certainty

    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
     echt
    -0.07
     opravdu
    -0.07
     practitioner
    -0.07
     delt
    -0.07
     diets
    -0.07
    up
    -0.06
    thes
    -0.06
    suite
    -0.06
    ảng
    -0.06
     Cres
    -0.06
    POSITIVE LOGITS
    -Allow
    0.06
    产业
    0.06
     amenities
    0.06
    ('/')[-
    0.06
    ทำ
    0.06
     IOError
    0.06
    으나
    0.06
     "",
    ↵
    0.06
     url
    0.06
     věcí
    0.06
    Activations Density 0.013%

    No Known Activations