© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 118578
    Prev
    Next
    INDEX
    Explanations

    Triple quotes

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Desired
    -0.07
    �
    -0.07
    ۲۸
    -0.07
    RX
    -0.07
    ivatel
    -0.06
    nivel
    -0.06
    ्यव
    -0.06
    ительной
    -0.06
     Ecuador
    -0.06
    Unload
    -0.06
    POSITIVE LOGITS
    ่อย
    0.07
    .HashMap
    0.07
     outnumber
    0.06
    _debug
    0.06
     Steph
    0.06
    <lemma
    0.06
     Респ
    0.06
    care
    0.06
    pora
    0.06
     맞
    0.06
    Activations Density 0.009%

    No Known Activations