© 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 (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 125509
    Prev
    Next
    INDEX
    Explanations

    foil

    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
     cooldown
    -0.07
     cruiser
    -0.07
    बर
    -0.06
    Decl
    -0.06
    ера
    -0.06
    _TRUNC
    -0.06
     TERM
    -0.06
    εφ
    -0.06
     связи
    -0.06
     gzip
    -0.06
    POSITIVE LOGITS
     Mus
    0.07
     flux
    0.06
     magically
    0.06
    foil
    0.06
    initWith
    0.06
     aylık
    0.06
     рецеп
    0.06
     adaptive
    0.06
    KindOfClass
    0.06
    iệng
    0.06
    Activations Density 0.003%

    No Known Activations