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. 7-RESID-POST-AA
    6. 34901
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hook
    -0.06
    Everything
    -0.06
    925
    -0.06
    _lp
    -0.06
    -that
    -0.06
    vised
    -0.06
     Kits
    -0.06
    寧
    -0.06
    _tuples
    -0.06
    _iv
    -0.06
    POSITIVE LOGITS
     prot
    0.07
    лаг
    0.07
    .substr
    0.07
     cac
    0.06
    .Panel
    0.06
    ひ
    0.06
     GAR
    0.06
    INPUT
    0.06
     psychiat
    0.06
     secondary
    0.06
    Activations Density 0.189%

    No Known Activations