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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 107916
    Prev
    Next
    INDEX
    Explanations

    orbit

    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
    Sparse
    -0.07
    Lou
    -0.07
     crud
    -0.07
     unpleasant
    -0.06
     dum
    -0.06
     cla
    -0.06
    Bien
    -0.06
    pression
    -0.06
     cond
    -0.06
     усіх
    -0.06
    POSITIVE LOGITS
     Orbit
    0.12
     orbit
    0.10
     orbits
    0.09
    bit
    0.07
     Coconut
    0.07
    BL
    0.07
    orbit
    0.07
     brilliantly
    0.06
    ither
    0.06
    织
    0.06
    Activations Density 0.005%

    No Known Activations