© 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. 49781
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ibar
    -0.07
    .SQL
    -0.06
    aft
    -0.06
    _almost
    -0.06
    ourney
    -0.06
    Sea
    -0.06
    .Number
    -0.06
     Enter
    -0.06
    ิลล
    -0.06
     الع
    -0.06
    POSITIVE LOGITS
     samostat
    0.07
     sheer
    0.06
     مخروط
    0.06
    Clr
    0.06
    579
    0.06
     nasıl
    0.06
    »،
    0.06
    .bumptech
    0.06
    .initState
    0.06
     luder
    0.06
    Activations Density 0.030%

    No Known Activations