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. 104365
    Prev
    Next
    INDEX
    Explanations

    abstract, intellectual topics

    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
    reflection
    -0.07
     shadows
    -0.07
     hakkında
    -0.07
     عباس
    -0.06
     altına
    -0.06
     CrossRef
    -0.06
    inciple
    -0.06
    Meeting
    -0.06
    oyo
    -0.06
     Latest
    -0.06
    POSITIVE LOGITS
     ))↵
    0.06
    .identity
    0.06
     implicit
    0.06
     OCC
    0.06
     install
    0.06
     рівня
    0.06
    ennen
    0.06
     marginal
    0.06
     han
    0.06
    auge
    0.06
    Activations Density 0.249%

    No Known Activations