© 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. 15-RESID-POST-AA
    6. 13024
    Prev
    Next
    INDEX
    Explanations

    Excerpts with numbers

    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
     서울
    -0.06
     上海
    -0.06
    monto
    -0.06
    ksam
    -0.06
    .sex
    -0.06
     přem
    -0.06
    gow
    -0.06
     Outlook
    -0.06
     شرکت
    -0.06
     All
    -0.06
    POSITIVE LOGITS
     tiết
    0.07
     unsubscribe
    0.07
     Mentor
    0.07
     writeFile
    0.06
     evaluated
    0.06
    Verification
    0.06
     Identified
    0.06
    INLINE
    0.06
     morals
    0.06
    Screenshot
    0.06
    Activations Density 0.000%

    No Known Activations