© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 5905
    Prev
    Next
    INDEX
    Explanations

    Data analysis/reporting

    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
    ynes
    -0.06
     surprised
    -0.06
     anew
    -0.06
     bake
    -0.06
     hủy
    -0.06
    isiert
    -0.06
    UILD
    -0.06
     intimacy
    -0.06
     Jo
    -0.06
    slave
    -0.06
    POSITIVE LOGITS
    -date
    0.07
    /MM
    0.07
    -names
    0.07
     hypoth
    0.07
    -security
    0.06
    Empleado
    0.06
    Write
    0.06
     injecting
    0.06
    Facade
    0.06
     software
    0.06
    Activations Density 0.000%

    No Known Activations