© 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. 27-RESID-POST-AA
    11. 102736
    Prev
    Next
    INDEX
    Explanations

    hotel reviews

    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
    (DB
    -0.07
    MSG
    -0.06
    =<?=
    -0.06
     BETWEEN
    -0.06
    052
    -0.06
     homeowners
    -0.06
     Inquiry
    -0.06
    ACA
    -0.06
     alignment
    -0.06
    ([↵
    -0.06
    POSITIVE LOGITS
    ')}</
    0.07
    .fromString
    0.07
     StringIO
    0.06
    price
    0.06
    你
    0.06
    固定
    0.06
     PropertyChangedEventArgs
    0.06
    ，你
    0.06
     ListViewItem
    0.06
     Intelli
    0.06
    Activations Density 0.110%

    No Known Activations