© 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. 19-RESID-POST-AA
    6. 59081
    Prev
    Next
    INDEX
    Explanations

    and

    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
    (vector
    -0.07
    isecond
    -0.07
    clipse
    -0.06
    _odd
    -0.06
    EventType
    -0.06
    	best
    -0.06
    Voice
    -0.06
     helpless
    -0.06
     frase
    -0.06
    antages
    -0.06
    POSITIVE LOGITS
     guessing
    0.06
     Поль
    0.06
     ورزش
    0.06
    кий
    0.06
    	Editor
    0.06
    σκ
    0.06
    ('_',
    0.06
     Deutschland
    0.06
     جلس
    0.06
     uç
    0.06
    Activations Density 0.189%

    No Known Activations