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. 11-RESID-POST-AA
    6. 93156
    Prev
    Next
    INDEX
    Explanations

    organizations

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ObjectOutputStream
    -0.06
    TEGR
    -0.06
    SJ
    -0.06
    通信
    -0.06
     most
    -0.06
    allocated
    -0.06
     sufficiently
    -0.06
    OTH
    -0.06
    哲
    -0.06
     بات
    -0.06
    POSITIVE LOGITS
    //}}
    0.07
    ırlar
    0.07
    .reason
    0.07
    \model
    0.06
     embarked
    0.06
    Ann
    0.06
     physicians
    0.06
    ґ
    0.06
    Tit
    0.06
    "is
    0.06
    Activations Density 0.113%

    No Known Activations