© 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. 7-RESID-POST-AA
    11. 80805
    Prev
    Next
    INDEX
    Explanations

    limits/limitations

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    movement
    -0.07
     caliber
    -0.06
     movements
    -0.06
    _prom
    -0.06
     Process
    -0.06
    аниц
    -0.06
    yl
    -0.06
    bia
    -0.06
    hold
    -0.06
     gradient
    -0.06
    POSITIVE LOGITS
     Messi
    0.07
     Lola
    0.07
    trasound
    0.06
     отказ
    0.06
    ---
↵
    0.06
    Sending
    0.06
     Ansi
    0.06
     mevcut
    0.06
     Chicago
    0.06
     Richmond
    0.06
    Activations Density 0.219%

    No Known Activations