© 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. 7-RESID-POST-AA
    11. 32159
    Prev
    Next
    INDEX
    Explanations

    vulgar

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mage
    -0.07
     رز
    -0.07
     Pony
    -0.07
     Rights
    -0.06
    ellido
    -0.06
     Moy
    -0.06
    _moves
    -0.06
    RITE
    -0.06
    ευση
    -0.06
    irit
    -0.06
    POSITIVE LOGITS
     vulgar
    0.15
     mundane
    0.08
     differ
    0.07
     provide
    0.07
     pagan
    0.06
    55
    0.06
     tpl
    0.06
    俗
    0.06
    104
    0.06
    login
    0.06
    Activations Density 0.003%

    No Known Activations