© 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. 73695
    Prev
    Next
    INDEX
    Explanations

    inventory/stock

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of inventory or stock control (e.g. the Portuguese “estoque” and related terms).

    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
    Unmount
    -0.07
    /platform
    -0.06
     ruthless
    -0.06
    efon
    -0.06
     signaling
    -0.06
    Su
    -0.06
    NibName
    -0.06
     Chop
    -0.06
     الکترون
    -0.06
     Agreement
    -0.06
    POSITIVE LOGITS
     müc
    0.07
     cis
    0.07
     frauen
    0.07
     gele
    0.06
    詞
    0.06
    ●
    0.06
     toplantı
    0.06
    _produk
    0.06
     kendisi
    0.06
    ­s
    0.06
    Activations Density 0.015%

    No Known Activations