© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 104007
    Prev
    Next
    INDEX
    Explanations

    infections and spores

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    имости
    -0.07
    urnished
    -0.07
     العديد
    -0.06
    ugi
    -0.06
    	events
    -0.06
     trộn
    -0.06
    换
    -0.06
     Update
    -0.06
    쳤다
    -0.06
     انتشار
    -0.06
    POSITIVE LOGITS
     �
    0.07
    .a
    0.07
     (_.
    0.07
    .board
    0.06
    _Struct
    0.06
     SU
    0.06
    [List
    0.06
    icone
    0.06
     behalf
    0.06
    <&
    0.06
    Activations Density 0.030%

    No Known Activations