© 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
    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. 79895
    Prev
    Next
    INDEX
    Explanations

    laxatives

    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
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’nda
    -0.07
    lon
    -0.07
    (Box
    -0.07
    plode
    -0.06
    @store
    -0.06
    Qué
    -0.06
    Police
    -0.06
    .pin
    -0.06
    /output
    -0.06
    ΄
    -0.06
    POSITIVE LOGITS
    atura
    0.07
    .helper
    0.06
    atures
    0.06
     Chand
    0.06
    camel
    0.06
     Ül
    0.06
    ature
    0.06
     mmap
    0.06
     application
    0.06
     applications
    0.06
    Activations Density 0.001%

    No Known Activations