© 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. 19-RESID-POST-AA
    11. 111644
    Prev
    Next
    INDEX
    Explanations

    that

    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
    _vars
    -0.06
     defining
    -0.06
     происходит
    -0.06
    una
    -0.06
     etraf
    -0.06
    uellen
    -0.06
    すれば
    -0.06
     बनन
    -0.06
     rising
    -0.06
     Os
    -0.06
    POSITIVE LOGITS
    .Filter
    0.07
     {↵
    0.07
    (Customer
    0.06
     <$
    0.06
     Kız
    0.06
    	price
    0.06
     vicious
    0.06
     Engineer
    0.06
    UIApplication
    0.06
    .entrySet
    0.06
    Activations Density 0.047%

    No Known Activations