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. 7-RESID-POST-AA
    6. 86664
    Prev
    Next
    INDEX
    Explanations

    band/spectral

    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
    -len
    -0.07
    يلاد
    -0.07
    serve
    -0.06
     enviar
    -0.06
     Nichols
    -0.06
     tons
    -0.06
    _feature
    -0.06
    	Command
    -0.06
    _latitude
    -0.06
     height
    -0.06
    POSITIVE LOGITS
    ologue
    0.07
    TimeString
    0.06
    (moment
    0.06
    286
    0.06
    ой
    0.06
    ��
    0.06
    _PROGRESS
    0.06
    (effect
    0.06
    inished
    0.06
    Products
    0.06
    Activations Density 0.017%

    No Known Activations