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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 109972
    Prev
    Next
    INDEX
    Explanations

    composition

    np_max-act · gemini-2.0-flash

    The neuron fires on the formal specification language of patent claims—especially functional verbs and phrases such as “comprises,” “provided,” “projected,” and similar claim-style descriptors.

    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
    aps
    -0.07
    _static
    -0.07
     IX
    -0.06
     Bars
    -0.06
     PSD
    -0.06
     set
    -0.06
    (where
    -0.06
     км
    -0.06
     inval
    -0.06
     choosing
    -0.06
    POSITIVE LOGITS
     χώ
    0.07
    (exports
    0.06
    ⠀⠀
    0.06
    塚
    0.06
    udson
    0.06
     consolidated
    0.06
    wyn
    0.06
     obsession
    0.06
    oran
    0.06
    Mom
    0.06
    Activations Density 0.027%

    No Known Activations