© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126766
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron fires on the “even the” fragment in the “without even the implied warranty…” clause commonly found in open-source license headers.

    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
    OUTPUT
    -0.07
     quá
    -0.07
    ्यव
    -0.06
    overall
    -0.06
     soğuk
    -0.06
    usually
    -0.06
    rido
    -0.06
     Printer
    -0.06
     الشخص
    -0.06
    _DETAIL
    -0.06
    POSITIVE LOGITS
     stě
    0.06
     Мед
    0.06
     wishes
    0.06
    ные
    0.06
     budeme
    0.06
    网
    0.06
     عد
    0.06
     dances
    0.06
     resolutions
    0.06
    _wc
    0.06
    Activations Density 0.002%

    No Known Activations