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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 46875
    Prev
    Next
    INDEX
    Explanations

    on

    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
    _gshared
    -0.07
    ppelin
    -0.07
     Со
    -0.06
     etmeye
    -0.06
     mají
    -0.06
     کسانی
    -0.06
    rál
    -0.06
     imageView
    -0.06
     đây
    -0.06
     RecognitionException
    -0.06
    POSITIVE LOGITS
     BORDER
    0.07
    (record
    0.07
     ako
    0.06
     Durham
    0.06
     manifesto
    0.06
    ি�
    0.06
     sélection
    0.06
     поз
    0.06
     competence
    0.06
    _routing
    0.06
    Activations Density 0.009%

    No Known Activations