Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 87035
    Prev
    Next
    INDEX
    Explanations

    floor

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     added
    -0.07
     oxide
    -0.07
    _text
    -0.07
     interacting
    -0.06
     Abdel
    -0.06
     English
    -0.06
     �
    -0.06
    عان
    -0.06
     serpent
    -0.06
     себе
    -0.06
    POSITIVE LOGITS
     floor
    0.16
     Floor
    0.12
     floors
    0.11
    -floor
    0.11
    Floor
    0.10
    floor
    0.10
    _floor
    0.09
    .Floor
    0.08
     flooring
    0.08
    .floor
    0.08
    Activations Density 0.007%

    No Known Activations