© 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. 6555
    Prev
    Next
    INDEX
    Explanations

    programming

    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
     resh
    -0.07
     Pear
    -0.07
    Chr
    -0.06
    uali
    -0.06
    jec
    -0.06
    _Part
    -0.06
    LastName
    -0.06
    _FR
    -0.06
     pict
    -0.06
     Cowboy
    -0.06
    POSITIVE LOGITS
    ervatives
    0.06
     getContent
    0.06
    性的
    0.06
     deterrent
    0.06
    Cloud
    0.06
    ifdef
    0.06
    いの
    0.06
     нічого
    0.06
     göre
    0.06
    τηγορία
    0.06
    Activations Density 0.322%

    No Known Activations