Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 103640
    Prev
    Next
    INDEX
    Explanations

    Brands and companies

    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
    科学
    -0.07
     路
    -0.06
    rod
    -0.06
    以下
    -0.06
     condemning
    -0.06
    IRD
    -0.06
    Ipv
    -0.06
    rodu
    -0.06
     rsa
    -0.06
     liebe
    -0.06
    POSITIVE LOGITS
    >`;↵
    0.06
    ってい
    0.06
     oč
    0.06
    upportInitialize
    0.06
     detainees
    0.06
    _brand
    0.06
    Undefined
    0.06
    _IEnumerator
    0.06
    }`;↵
    0.06
     meses
    0.06
    Activations Density 0.017%

    No Known Activations