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. 11-RESID-POST-AA
    6. 93094
    Prev
    Next
    INDEX
    Explanations

    programming discussions

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _Address
    -0.07
    838
    -0.07
    greSQL
    -0.06
    .Pixel
    -0.06
    necessary
    -0.06
     hayat
    -0.06
     Drop
    -0.06
    .circle
    -0.06
     filePath
    -0.06
    737
    -0.06
    POSITIVE LOGITS
    QS
    0.07
     edeb
    0.06
     отказ
    0.06
    ília
    0.06
     inund
    0.06
     ‫
    0.06
    аксим
    0.06
     kicked
    0.06
    ellation
    0.06
    ная
    0.06
    Activations Density 0.300%

    No Known Activations