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. 10400
    Prev
    Next
    INDEX
    Explanations

    to

    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
     curves
    -0.07
    054
    -0.06
    อว
    -0.06
    zilla
    -0.06
     Jac
    -0.06
    Article
    -0.06
     lecture
    -0.06
    аков
    -0.06
    plevel
    -0.06
     Username
    -0.06
    POSITIVE LOGITS
     čist
    0.07
     genellikle
    0.07
    iverz
    0.07
     Persian
    0.07
     intolerance
    0.07
    (Controller
    0.07
     contraception
    0.06
     xOffset
    0.06
    (slot
    0.06
    لق
    0.06
    Activations Density 0.007%

    No Known Activations