© 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. 11-RESID-POST-AA
    11. 123895
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    :::::
    -0.07
    aises
    -0.06
    ']}'
    -0.06
    _decimal
    -0.06
    (Dictionary
    -0.06
     кількості
    -0.06
     statuses
    -0.06
    ftar
    -0.06
     assessment
    -0.06
     chiế
    -0.06
    POSITIVE LOGITS
     Acquisition
    0.06
     yap
    0.06
    )',↵
    0.06
     indu
    0.06
     timp
    0.06
     il
    0.06
    /The
    0.06
     accent
    0.06
    _do
    0.06
    !,↵
    0.06
    Activations Density 0.004%

    No Known Activations