© 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. 7-RESID-POST-AA
    6. 118689
    Prev
    Next
    INDEX
    Explanations

    coca

    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
    儀
    -0.07
     كرد
    -0.06
    	setTimeout
    -0.06
     asleep
    -0.06
     Wash
    -0.06
    ерим
    -0.06
    _AUTH
    -0.06
     indign
    -0.06
     arkadaş
    -0.06
     десят
    -0.06
    POSITIVE LOGITS
     Coca
    0.15
     ecological
    0.08
    oca
    0.07
    Canon
    0.07
    )!=
    0.07
    sparse
    0.07
                
    ↵
    0.07
     accept
    0.06
    iquement
    0.06
     Suc
    0.06
    Activations Density 0.000%

    No Known Activations