© 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. 51841
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
     заним
    -0.08
    (k
    -0.07
    محمد
    -0.07
     Connected
    -0.07
    fold
    -0.06
     eher
    -0.06
    爷
    -0.06
     lisans
    -0.06
     Forge
    -0.06
     acad
    -0.06
    POSITIVE LOGITS
    .Input
    0.07
     danych
    0.06
    .param
    0.06
    arding
    0.06
    Nota
    0.06
    caster
    0.06
     Options
    0.06
    olik
    0.06
    RF
    0.06
     Dah
    0.06
    Activations Density 0.006%

    No Known Activations