© 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. 3-RESID-POST-AA
    6. 95656
    Prev
    Next
    INDEX
    Explanations

    to

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itemCount
    -0.07
     خور
    -0.07
     пад
    -0.07
    NodeType
    -0.06
    )+"
    -0.06
     blaze
    -0.06
     spikes
    -0.06
    /mL
    -0.06
     sıcak
    -0.06
     brick
    -0.06
    POSITIVE LOGITS
    $app
    0.06
     gastr
    0.06
    ental
    0.06
    كات
    0.06
    ofstream
    0.06
    Strange
    0.06
    Omega
    0.06
     Mus
    0.06
    “The
    0.06
    $criteria
    0.06
    Activations Density 0.102%

    No Known Activations