© 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. 68845
    Prev
    Next
    INDEX
    Explanations

    online websites

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of online or web‐based publication contexts (e.g. “online,” “web,” “website,” “.com”).

    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
    aran
    -0.07
    inally
    -0.07
     USD
    -0.07
     Compensation
    -0.07
     Language
    -0.07
    bbbb
    -0.06
     Loren
    -0.06
     Regel
    -0.06
    Boston
    -0.06
     terminated
    -0.06
    POSITIVE LOGITS
    _permalink
    0.07
    toolbar
    0.06
     altern
    0.06
     enctype
    0.06
     CircularProgressIndicator
    0.06
     ch
    0.06
     �
    0.06
     standout
    0.06
     пенс
    0.06
     DVD
    0.06
    Activations Density 0.025%

    No Known Activations