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. 23-RESID-POST-AA
    6. 104021
    Prev
    Next
    INDEX
    Explanations

    sanct

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     고개를
    -0.07
     deform
    -0.07
    沉
    -0.07
     puppies
    -0.06
     prescriptions
    -0.06
    CONTEXT
    -0.06
    Emily
    -0.06
    /********
    -0.06
     redhead
    -0.06
    Matthew
    -0.06
    POSITIVE LOGITS
     pek
    0.07
    inki
    0.06
    -I
    0.06
    .Inst
    0.06
    -Man
    0.06
     bảo
    0.06
    -building
    0.06
     کسانی
    0.06
     porter
    0.06
    сті
    0.06
    Activations Density 0.001%

    No Known Activations