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. 59866
    Prev
    Next
    INDEX
    Explanations

    C++ strings

    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
     alphanumeric
    -0.07
     процесс
    -0.06
     altın
    -0.06
    .WinControls
    -0.06
    村
    -0.06
    ("{
    -0.06
    -zA
    -0.06
    φι
    -0.06
    桥
    -0.06
    ==>
    -0.06
    POSITIVE LOGITS
     olacak
    0.07
     contrat
    0.07
     Sanchez
    0.07
     ชนะ
    0.06
     Castillo
    0.06
     (-
    0.06
     sexy
    0.06
     paj
    0.06
    avs
    0.06
    Ns
    0.06
    Activations Density 0.072%

    No Known Activations