© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 52467
    Prev
    Next
    INDEX
    Explanations

    val

    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
    _edit
    -0.07
     shirt
    -0.06
     Numerous
    -0.06
    .cert
    -0.06
    creasing
    -0.06
    _Template
    -0.06
    :function
    -0.06
     være
    -0.06
    (row
    -0.06
     редак
    -0.06
    POSITIVE LOGITS
    _parallel
    0.08
    MAL
    0.07
     maç
    0.06
    ardown
    0.06
    _boot
    0.06
    haf
    0.06
    QL
    0.06
     vere
    0.06
     autonomy
    0.06
    ôt
    0.06
    Activations Density 0.007%

    No Known Activations