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. 27-RESID-POST-AA
    6. 102049
    Prev
    Next
    INDEX
    Explanations

    say ")"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     belonging
    -0.06
    σω
    -0.06
    atility
    -0.06
     Rolled
    -0.06
     рядом
    -0.06
    -cut
    -0.06
     porque
    -0.06
     Cut
    -0.06
     impose
    -0.06
    -slide
    -0.06
    POSITIVE LOGITS
    mě
    0.07
    _mono
    0.07
    .ToDateTime
    0.07
     حافظه
    0.07
    AE
    0.06
     เน
    0.06
    AC
    0.06
    metro
    0.06
    ConverterFactory
    0.06
     leh
    0.06
    Activations Density 0.044%

    No Known Activations