© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 619
    Prev
    Next
    INDEX
    Explanations

    tumor

    np_max-act · gemini-2.0-flash

    The neuron is primarily activated by mentions of “tumor” (including variant spellings like “tumour” and related forms).

    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
    _SYMBOL
    -0.07
    OrCreate
    -0.06
    owned
    -0.06
    getResponse
    -0.06
    POWER
    -0.06
    ΡΙ
    -0.06
    _crop
    -0.06
     Serializer
    -0.06
    ERP
    -0.06
    وست
    -0.06
    POSITIVE LOGITS
     tum
    0.07
     intermitt
    0.07
     nel
    0.06
    ',"
    0.06
    tab
    0.06
    .datab
    0.06
    (save
    0.06
    _Image
    0.06
     Tmax
    0.06
    865
    0.06
    Activations Density 0.005%

    No Known Activations