© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 15757
    Prev
    Next
    INDEX
    Explanations

    mass

    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
     쉽
    -0.08
     let
    -0.08
     вет
    -0.07
    -minute
    -0.07
    서울
    -0.07
     dět
    -0.07
     Todo
    -0.07
     unde
    -0.07
    _xt
    -0.06
     startling
    -0.06
    POSITIVE LOGITS
     mass
    0.10
     Mass
    0.10
    Mass
    0.09
    IS
    0.09
    ISS
    0.08
     MASS
    0.08
    排
    0.07
    amps
    0.07
     Harris
    0.07
    iss
    0.07
    Activations Density 0.026%

    No Known Activations