© 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. 42655
    Prev
    Next
    INDEX
    Explanations

    methods to resolve problems

    np_max-act · gemini-2.0-flash

    The neuron detects language advocating peaceful, humane conflict resolution (e.g. “gestire i problemi in modo pacifico e umano”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     zejména
    -0.07
    .userid
    -0.07
    at
    -0.06
    Ki
    -0.06
     tore
    -0.06
    124
    -0.06
     fiz
    -0.06
     हज
    -0.06
    ้าก
    -0.06
     lul
    -0.06
    POSITIVE LOGITS
     tabela
    0.07
    енти
    0.07
    icky
    0.06
    __
    0.06
    ンティ
    0.06
    perms
    0.06
    <Guid
    0.06
    _TBL
    0.06
     Hispan
    0.06
    alytics
    0.06
    Activations Density 0.024%

    No Known Activations