© 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. 3-RESID-POST-AA
    11. 121908
    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     which
    -0.06
    Compute
    -0.06
    Remarks
    -0.06
     continuation
    -0.06
    _buffers
    -0.06
    _inputs
    -0.06
     commune
    -0.06
    etermine
    -0.06
    tutorial
    -0.06
     hookup
    -0.06
    POSITIVE LOGITS
    LER
    0.07
    taj
    0.07
     대회
    0.07
    lis
    0.07
     plugged
    0.06
    ler
    0.06
     reflective
    0.06
     Oakland
    0.06
     Volk
    0.06
    /*@
    0.06
    Activations Density 0.023%

    No Known Activations