© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 69154
    Prev
    Next
    INDEX
    Explanations

    a

    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
     dank
    -0.08
    pest
    -0.07
    unes
    -0.07
    ひと
    -0.07
    ुण
    -0.07
    icult
    -0.06
    CCR
    -0.06
     solar
    -0.06
    -information
    -0.06
    degrees
    -0.06
    POSITIVE LOGITS
     premiere
    0.07
    引き
    0.06
    陈
    0.06
    (true
    0.06
     виг
    0.06
    .isEnabled
    0.06
     TILE
    0.06
     Statement
    0.06
    Two
    0.05
     trục
    0.05
    Activations Density 0.001%

    No Known Activations