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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 98691
    Prev
    Next
    INDEX
    Explanations

    wines/vineyards

    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
    identification
    -0.07
    _copy
    -0.07
     dict
    -0.06
    contents
    -0.06
    imenti
    -0.06
    Settings
    -0.06
     equipment
    -0.06
    ani
    -0.06
    (dictionary
    -0.06
    -desc
    -0.06
    POSITIVE LOGITS
     SAM
    0.07
    <=$
    0.07
     �
    0.07
     exceptionally
    0.07
    (ST
    0.06
     puzzles
    0.06
     тол
    0.06
    InMillis
    0.06
    =min
    0.06
     ModelState
    0.06
    Activations Density 0.009%

    No Known Activations