© 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. 95503
    Prev
    Next
    INDEX
    Explanations

    const

    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
    (or
    -0.07
     Korean
    -0.07
     menjadi
    -0.07
    zel
    -0.06
    初
    -0.06
     Ryu
    -0.06
     دخ
    -0.06
     smoked
    -0.06
    塑
    -0.06
     Tempo
    -0.06
    POSITIVE LOGITS
     const
    0.09
    )const
    0.08
     ''),↵
    0.07
    	const
    0.07
     NDEBUG
    0.07
     noexcept
    0.06
    ")){
↵
    0.06
    ulması
    0.06
     Persons
    0.06
    LOTS
    0.06
    Activations Density 0.003%

    No Known Activations