Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 9811
    Prev
    Next
    INDEX
    Explanations

    Regulations and city planning

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cavern
    -0.07
     Sez
    -0.07
     cultured
    -0.07
    _vec
    -0.07
    adem
    -0.06
     présent
    -0.06
     dorm
    -0.06
     baud
    -0.06
     уровне
    -0.06
     clouds
    -0.06
    POSITIVE LOGITS
     bailout
    0.07
    /ph
    0.06
     ni
    0.06
    /tr
    0.06
    uled
    0.06
    WHITE
    0.06
     ();
    ↵
    0.06
    :n
    0.06
    pgsql
    0.06
     Iss
    0.06
    Activations Density 0.000%

    No Known Activations