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. 28794
    Prev
    Next
    INDEX
    Explanations

    in

    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
     ارتف
    -0.06
    orsche
    -0.06
     Km
    -0.06
     الطب
    -0.06
     یافته
    -0.06
    ıb
    -0.06
    Kevin
    -0.06
     concl
    -0.06
     lugar
    -0.06
     Yug
    -0.06
    POSITIVE LOGITS
    alen
    0.08
     Sonata
    0.07
     Friends
    0.06
    ;"><
    0.06
    eler
    0.06
    ­n
    0.06
    enen
    0.06
    elen
    0.06
    .Un
    0.06
    ,on
    0.06
    Activations Density 0.010%

    No Known Activations