© 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. 15-RESID-POST-AA
    6. 126688
    Prev
    Next
    INDEX
    Explanations

    descriptions

    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
     breeds
    -0.07
    ंतर
    -0.06
    .contact
    -0.06
    антаж
    -0.06
    velop
    -0.06
    Classic
    -0.06
     Minimum
    -0.06
     Dos
    -0.06
     ♥
    -0.06
     ด
    -0.06
    POSITIVE LOGITS
    ()?;↵
    0.07
     doldur
    0.06
     PSI
    0.06
    治疗
    0.06
    HASH
    0.06
     initialise
    0.06
     advertisements
    0.06
     Campbell
    0.06
    opa
    0.06
     حزب
    0.06
    Activations Density 0.105%

    No Known Activations