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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15-RESID-POST-AA
    11. 24179
    Prev
    Next
    INDEX
    Explanations

    moderation

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.07
    continent
    -0.06
     Bingo
    -0.06
     defective
    -0.06
     TMP
    -0.06
    MAL
    -0.06
     cellul
    -0.06
    �
    -0.06
     köy
    -0.06
    _XDECREF
    -0.06
    POSITIVE LOGITS
    gregator
    0.08
     conducted
    0.08
    Tại
    0.07
    ofire
    0.07
     IPCC
    0.07
     raise
    0.07
    .href
    0.07
     curated
    0.07
    REFER
    0.07
    Howard
    0.07
    Activations Density 0.004%

    No Known Activations