© 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. 8015
    Prev
    Next
    INDEX
    Explanations

    "="

    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
    aviolet
    -0.07
     createStore
    -0.06
     ấm
    -0.06
     Eco
    -0.06
    objet
    -0.06
    making
    -0.06
     microscopic
    -0.06
    @Bean
    -0.06
    /py
    -0.06
    しかし
    -0.06
    POSITIVE LOGITS
    _Float
    0.07
     '';
    0.07
    ...",↵
    0.07
     ];↵
    0.06
    .Once
    0.06
     during
    0.06
    .Cache
    0.06
     ABOVE
    0.06
     Horse
    0.06
     Hotels
    0.06
    Activations Density 0.017%

    No Known Activations