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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 103105
    Prev
    Next
    INDEX
    Explanations

    see

    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
     dù
    -0.07
    lero
    -0.07
    notification
    -0.07
     trails
    -0.07
    лим
    -0.07
    Based
    -0.06
     dir
    -0.06
    berg
    -0.06
     Gan
    -0.06
    他
    -0.06
    POSITIVE LOGITS
    "g
    0.07
     vytvá
    0.07
    metic
    0.07
     /************************************************************************
    0.06
     indulge
    0.06
     Objective
    0.06
     "]
    0.06
    наслід
    0.06
     знай
    0.06
    fstream
    0.06
    Activations Density 0.150%

    No Known Activations