© 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. 15-RESID-POST-AA
    11. 37260
    Prev
    Next
    INDEX
    Explanations

    Dates and versions

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reconstruction
    -0.08
     Agricultural
    -0.07
     celebrity
    -0.07
     cutting
    -0.07
     foregoing
    -0.07
    Pretty
    -0.06
    SID
    -0.06
     Anton
    -0.06
     EventType
    -0.06
     franchise
    -0.06
    POSITIVE LOGITS
    ạn
    0.06
    enance
    0.06
    /plain
    0.06
    bbbb
    0.06
     '',
↵
    0.06
    IGNORE
    0.06
     तब
    0.06
    ub
    0.06
     russe
    0.06
    (ind
    0.05
    Activations Density 0.248%

    No Known Activations