© 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. 129695
    Prev
    Next
    INDEX
    Explanations

    tool

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of scientific methods and instruments (e.g. microscopy techniques, assays, “tool,” “methodology,” and other methodological 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
    ,",
    -0.07
     onions
    -0.06
     Malik
    -0.06
    .wav
    -0.06
     fon
    -0.06
     embryos
    -0.06
     tomato
    -0.06
     tolerance
    -0.06
    _alarm
    -0.06
     statue
    -0.06
    POSITIVE LOGITS
     Mov
    0.06
     başar
    0.06
     UICollectionView
    0.06
    $fields
    0.06
    �
    0.06
     chỉ
    0.06
     Maurit
    0.06
    Unlock
    0.06
     Supplementary
    0.06
     پی
    0.06
    Activations Density 0.058%

    No Known Activations