© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 52810
    Prev
    Next
    INDEX
    Explanations

    website routes

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monitor
    -0.07
    utory
    -0.07
     leaking
    -0.07
    Check
    -0.06
    994
    -0.06
    _RA
    -0.06
    _Search
    -0.06
    _AR
    -0.06
    _profile
    -0.06
     honors
    -0.06
    POSITIVE LOGITS
     академ
    0.06
     ~
    0.06
     вода
    0.06
    etros
    0.06
    (csv
    0.06
     {\↵
    0.06
     عدد
    0.06
     prot
    0.06
    êu
    0.06
     kabul
    0.06
    Activations Density 0.004%

    No Known Activations