© 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
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 127023
    Prev
    Next
    INDEX
    Explanations

    that

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    textView
    -0.08
    ку
    -0.07
    _unit
    -0.06
     produ
    -0.06
     kone
    -0.06
     ข
    -0.06
     gan
    -0.06
    ))^
    -0.06
    今日
    -0.06
    ерп
    -0.06
    POSITIVE LOGITS
    aptured
    0.07
     carrier
    0.06
    .Wh
    0.06
     अब
    0.06
     AUG
    0.06
    .getMethod
    0.06
    .related
    0.06
    SS
    0.06
    =="
    0.06
    .community
    0.06
    Activations Density 0.176%

    No Known Activations