© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 101437
    Prev
    Next
    INDEX
    Explanations

    Ordinal rankings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    าคาร
    -0.07
    描述
    -0.07
    isEnabled
    -0.06
    .destroyAllWindows
    -0.06
    .AutoComplete
    -0.06
     taxonomy
    -0.06
     Mort
    -0.06
    _ary
    -0.06
    -through
    -0.06
    	redirect
    -0.06
    POSITIVE LOGITS
    (sig
    0.07
     hmot
    0.07
     langue
    0.06
    oute
    0.06
     ))
    0.06
    วไป
    0.06
    Muon
    0.06
    osal
    0.06
    حث
    0.06
     nymph
    0.06
    Activations Density 0.007%

    No Known Activations