© 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. 15-RESID-POST-AA
    6. 60694
    Prev
    Next
    INDEX
    Explanations

    Reports and studies

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     findById
    -0.07
    Grammar
    -0.07
     Mario
    -0.06
    _special
    -0.06
    nelly
    -0.06
     postup
    -0.06
     Franco
    -0.06
     İşte
    -0.06
    cam
    -0.06
     l
    -0.06
    POSITIVE LOGITS
    poll
    0.07
    lected
    0.06
    обыти
    0.06
     creatures
    0.06
    าย
    0.06
     женщин
    0.06
     backers
    0.06
    (texture
    0.06
    .QRect
    0.06
     animator
    0.06
    Activations Density 0.274%

    No Known Activations