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. 15-RESID-POST-AA
    6. 122475
    Prev
    Next
    INDEX
    Explanations

    LSTM

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _scope
    -0.07
    Space
    -0.07
     hoax
    -0.07
    az
    -0.07
     repar
    -0.06
     Wei
    -0.06
     ZERO
    -0.06
     Dani
    -0.06
    收入
    -0.06
     xanh
    -0.06
    POSITIVE LOGITS
     timestamps
    0.07
    ,因此
    0.07
    .П
    0.07
    шт
    0.07
    .rest
    0.06
    uhl
    0.06
     Last
    0.06
    !!}</
    0.06
    slu
    0.06
    ательных
    0.06
    Activations Density 0.002%

    No Known Activations