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. 85329
    Prev
    Next
    INDEX
    Explanations

    contract clauses

    np_max-act · gemini-2.0-flash

    This neuron activates on terms naming or describing contractual provisions—words like “clause,” “contract,” “condition,” “limitation,” and related enforceability language.

    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
    ithe
    -0.07
    _WORLD
    -0.07
    _rec
    -0.06
    ViewState
    -0.06
    *@
    -0.06
    ract
    -0.06
    626
    -0.06
    جم
    -0.06
    #=
    -0.06
    Ted
    -0.06
    POSITIVE LOGITS
    占
    0.07
     إلي
    0.06
     GRA
    0.06
     downstream
    0.06
     Que
    0.06
     PIC
    0.06
    Submitting
    0.06
    роч
    0.06
     InputDecoration
    0.06
    .clean
    0.06
    Activations Density 0.011%

    No Known Activations