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. 30666
    Prev
    Next
    INDEX
    Explanations

    Years in 2000s

    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
    POSITE
    -0.06
    (nil
    -0.06
     Verified
    -0.06
     protester
    -0.06
    hevik
    -0.06
     replaced
    -0.06
     Put
    -0.06
     libro
    -0.06
    _mu
    -0.06
     Thorn
    -0.06
    POSITIVE LOGITS
    ↵
    0.06
     eag
    0.06
    bote
    0.06
    .sem
    0.06
    icho
    0.06
    .MONTH
    0.06
    rente
    0.06
    (short
    0.06
     silky
    0.06
    agements
    0.06
    Activations Density 0.020%

    No Known Activations