© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 79082
    Prev
    Next
    INDEX
    Explanations

    url or classname

    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
     دن
    -0.07
    _spell
    -0.06
    ColumnType
    -0.06
     갑
    -0.06
     cafeteria
    -0.06
    /*================================================================
    -0.06
    COMPLETE
    -0.06
    광
    -0.05
    benchmark
    -0.05
    )sender
    -0.05
    POSITIVE LOGITS
     Nic
    0.07
    _put
    0.07
    Indices
    0.07
     &'
    0.07
     stepped
    0.07
     goto
    0.07
     concluding
    0.07
     gravitational
    0.06
     Json
    0.06
    /pro
    0.06
    Activations Density 0.005%

    No Known Activations