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. 19-RESID-POST-AA
    6. 9952
    Prev
    Next
    INDEX
    Explanations

    names

    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
    	conf
    -0.06
     Du
    -0.06
    Twig
    -0.06
    림
    -0.06
     ص
    -0.06
    La
    -0.06
     q
    -0.06
     reduces
    -0.06
    interest
    -0.06
    _HEADER
    -0.06
    POSITIVE LOGITS
    HOST
    0.07
    _sent
    0.07
    -focus
    0.06
     giving
    0.06
    higher
    0.06
    (project
    0.06
     instinct
    0.06
    /package
    0.06
    APSHOT
    0.06
    (validation
    0.06
    Activations Density 0.051%

    No Known Activations