© 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. 23-RESID-POST-AA
    6. 29944
    Prev
    Next
    INDEX
    Explanations

    ase

    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
     Bis
    -0.07
     library
    -0.06
    Been
    -0.06
    ündeki
    -0.06
     folklore
    -0.06
     inhibitors
    -0.06
     attorneys
    -0.06
    orneys
    -0.06
     binary
    -0.06
    推荐
    -0.06
    POSITIVE LOGITS
    aes
    0.08
     domest
    0.07
     Wak
    0.07
    arResult
    0.07
    ��
    0.07
    .Reg
    0.07
    ae
    0.07
    _ENT
    0.07
    ash
    0.07
    ASE
    0.07
    Activations Density 0.005%

    No Known Activations