© 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. 90823
    Prev
    Next
    INDEX
    Explanations

    chemical compounds

    np_max-act · gemini-2.0-flash

    This neuron activates on parts of systematic chemical compound names (IUPAC-style nomenclature).

    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
    уття
    -0.06
    	ap
    -0.06
    rylic
    -0.06
    ////
    -0.06
    �
    -0.06
     практически
    -0.06
    [ix
    -0.06
     ActiveSupport
    -0.06
     invisible
    -0.06
    )-(
    -0.06
    POSITIVE LOGITS
     lin
    0.09
     at
    0.07
     xnxx
    0.06
     by
    0.06
     the
    0.06
    (_.
    0.06
    *****↵
    0.06
     Unit
    0.06
     обязатель
    0.06
    ...,
    0.06
    Activations Density 0.034%

    No Known Activations