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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-RESID-POST-AA
    6. 57275
    Prev
    Next
    INDEX
    Explanations

    firearms

    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
    YouTube
    -0.07
    angled
    -0.07
    orem
    -0.07
     considering
    -0.06
    -drive
    -0.06
     possessed
    -0.06
     problème
    -0.06
    container
    -0.06
    gens
    -0.06
     hundreds
    -0.06
    POSITIVE LOGITS
    antlr
    0.07
     JAXBElement
    0.07
    eways
    0.06
     HttpSession
    0.06
    .Ui
    0.06
     fk
    0.06
     ContentValues
    0.06
    _AspNet
    0.06
    孝
    0.06
    .Infof
    0.06
    Activations Density 0.046%

    No Known Activations