© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42614
    Prev
    Next
    INDEX
    Explanations

    lack of permission/knowledge

    np_max-act · gemini-2.0-flash

    This neuron activates on phrasing that indicates something done without a person’s consent or knowledge.

    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
     sessionStorage
    -0.07
     Islanders
    -0.07
    ों
    -0.07
    IPv
    -0.07
    LocalStorage
    -0.07
     FK
    -0.07
    phasis
    -0.06
    BoundingBox
    -0.06
    _DSP
    -0.06
     Anyway
    -0.06
    POSITIVE LOGITS
     norm
    0.07
     ders
    0.06
    makes
    0.06
     Books
    0.06
     captain
    0.06
     rough
    0.06
     slightly
    0.06
     Wort
    0.06
    ismo
    0.06
    amer
    0.06
    Activations Density 0.019%

    No Known Activations