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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RESID-POST-AA
    6. 22329
    Prev
    Next
    INDEX
    Explanations

    to

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocused
    -0.06
     outras
    -0.06
    _Project
    -0.06
    :UIControlEventTouchUpInside
    -0.06
    Mur
    -0.06
     Agility
    -0.06
    rowable
    -0.05
    Cars
    -0.05
     MULT
    -0.05
    .us
    -0.05
    POSITIVE LOGITS
    ฟ
    0.07
     Cumhuriyeti
    0.07
     fondo
    0.07
    锦
    0.07
     fertilizer
    0.07
    perm
    0.06
     răng
    0.06
    去
    0.06
    perse
    0.06
     synonyms
    0.06
    Activations Density 0.017%

    No Known Activations