© 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. 83400
    Prev
    Next
    INDEX
    Explanations

    ="

    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
     yen
    -0.07
     quits
    -0.07
    %%%
    -0.07
     confl
    -0.07
     умов
    -0.07
    (con
    -0.06
     forthcoming
    -0.06
     mad
    -0.06
     prog
    -0.06
    %
    -0.06
    POSITIVE LOGITS
    asionally
    0.07
     चर
    0.07
    Descriptors
    0.07
    �
    0.06
    SERVER
    0.06
    lsruhe
    0.06
    (option
    0.06
     lesbische
    0.06
    ellschaft
    0.06
     Steering
    0.06
    Activations Density 0.002%

    No Known Activations