© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 55690
    Prev
    Next
    INDEX
    Explanations

    something

    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
    irty
    -0.07
     kont
    -0.07
     conforme
    -0.07
    _cluster
    -0.06
    (se
    -0.06
    _namespace
    -0.06
    _nsec
    -0.06
     rex
    -0.06
     koy
    -0.06
    ternal
    -0.06
    POSITIVE LOGITS
    :.
    0.06
    čemž
    0.06
    Need
    0.06
     продукт
    0.06
     Escape
    0.06
     Worst
    0.05
     equipments
    0.05
     шаг
    0.05
     suche
    0.05
    diğini
    0.05
    Activations Density 0.029%

    No Known Activations