© 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. 8858
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash

    The neuron is chiefly triggered by geographic place names (e.g. “Ukraine,” “Africa”).

    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
     kısa
    -0.07
    ION
    -0.07
    filt
    -0.06
     القر
    -0.06
    ỏ
    -0.06
     předpis
    -0.06
    ança
    -0.06
    82
    -0.06
     合
    -0.06
     Ek
    -0.06
    POSITIVE LOGITS
    λευ
    0.06
     öl
    0.06
     Slee
    0.06
     nodeList
    0.06
     Sicher
    0.06
    边
    0.06
    OfBirth
    0.06
    educt
    0.06
    شن
    0.06
    .extent
    0.06
    Activations Density 0.149%

    No Known Activations