© 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. 127170
    Prev
    Next
    INDEX
    Explanations

    input

    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
     cameras
    -0.07
    站
    -0.07
    	ctx
    -0.07
    BST
    -0.07
     nud
    -0.07
    center
    -0.06
     Uygu
    -0.06
    exclude
    -0.06
     paper
    -0.06
    abcdefghijklmnopqrstuvwxyz
    -0.06
    POSITIVE LOGITS
     flere
    0.07
    $IFn
    0.06
     grosse
    0.06
    teş
    0.06
     Alexandre
    0.06
     Fairfield
    0.06
     NSLocalizedString
    0.06
    AndUpdate
    0.06
    AndGet
    0.06
     newItem
    0.06
    Activations Density 0.014%

    No Known Activations