Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 124952
    Prev
    Next
    INDEX
    Explanations

    functionality testing

    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
     method
    -0.07
     questionable
    -0.07
     Mercury
    -0.06
     Devin
    -0.06
    -method
    -0.06
     tanggal
    -0.06
     hatred
    -0.06
     rubble
    -0.06
     impactful
    -0.06
    isset
    -0.06
    POSITIVE LOGITS
     Bair
    0.06
     батьків
    0.06
     vrouw
    0.06
    .projects
    0.06
    ởi
    0.06
    (STD
    0.06
     ncols
    0.06
    BoundingClientRect
    0.06
     можлив
    0.06
    nonatomic
    0.06
    Activations Density 0.036%

    No Known Activations