Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 110785
    Prev
    Next
    INDEX
    Explanations

    complex topics

    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
     mesure
    -0.07
     according
    -0.07
    fieldset
    -0.07
     С
    -0.07
    ystone
    -0.07
     bitrate
    -0.06
     faz
    -0.06
    Thousands
    -0.06
     fica
    -0.06
     σύ
    -0.06
    POSITIVE LOGITS
    _human
    0.07
    ()%
    0.07
    ASN
    0.06
    ÃO
    0.06
    OLF
    0.06
    adt
    0.06
    omen
    0.06
     {[%
    0.06
    LM
    0.06
     WebView
    0.06
    Activations Density 0.267%

    No Known Activations