© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 105696
    Prev
    Next
    INDEX
    Explanations

    500

    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
     overdose
    -0.07
     хочу
    -0.06
    (tb
    -0.06
    ationToken
    -0.06
    QC
    -0.06
     flaming
    -0.06
     disconnect
    -0.06
     oversees
    -0.06
     inFile
    -0.06
    imde
    -0.06
    POSITIVE LOGITS
    iag
    0.07
     Programming
    0.07
    .fullName
    0.07
    air
    0.07
    ,false
    0.06
    اس
    0.06
    .recipe
    0.06
    _QUERY
    0.06
     fuller
    0.06
     Holdings
    0.06
    Activations Density 0.113%

    No Known Activations