© 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
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 95459
    Prev
    Next
    INDEX
    Explanations

    Moon

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kutje
    -0.08
    สถ
    -0.07
     *__
    -0.06
     Raf
    -0.06
    cılık
    -0.06
    迅
    -0.06
    crawl
    -0.06
     Crit
    -0.06
    ��取
    -0.06
     Mash
    -0.06
    POSITIVE LOGITS
     Moon
    0.35
    Moon
    0.27
     moon
    0.24
    moon
    0.15
    oon
    0.10
     moons
    0.08
     honeymoon
    0.08
     lunar
    0.08
     sóng
    0.07
    情
    0.07
    Activations Density 0.005%

    No Known Activations