Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 125692
    Prev
    Next
    INDEX
    Explanations

    Business and technology

    np_max-act · gemini-2.0-flash

    The neuron fires on modal and speculative expressions (e.g. could, may, would, risking) that signal possibilities or proposals in business/strategic contexts.

    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
     Ning
    -0.07
    損
    -0.07
     نشده
    -0.06
    erc
    -0.06
    υχ
    -0.06
    ін
    -0.06
    _gchandle
    -0.06
    reating
    -0.06
     encoder
    -0.06
    раг
    -0.06
    POSITIVE LOGITS
     clit
    0.07
     gray
    0.07
    ูแล
    0.07
     Important
    0.06
     "\\"
    0.06
    grey
    0.06
    .ActionListener
    0.06
    	define
    0.06
     Cannot
    0.06
    ╝
    0.06
    Activations Density 0.053%

    No Known Activations