© 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. 7335
    Prev
    Next
    INDEX
    Explanations

    201

    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
    νηση
    -0.07
    Fre
    -0.07
    Ns
    -0.07
    OP
    -0.07
     СССР
    -0.07
    ัท
    -0.07
    НО
    -0.07
    ネ
    -0.06
    ный
    -0.06
    _employee
    -0.06
    POSITIVE LOGITS
    	speed
    0.08
     recounts
    0.07
    regunta
    0.06
    $tpl
    0.06
     Wayback
    0.06
     إي
    0.06
     유지
    0.06
    getWindow
    0.06
    buttonShape
    0.06
    	anim
    0.06
    Activations Density 0.003%

    No Known Activations