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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 84484
    Prev
    Next
    INDEX
    Explanations

    get

    np_max-act · gemini-2.0-flash

    The neuron activates on C# property getter declarations (the “get” accessors in property definitions).

    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
    久
    -0.07
    .convert
    -0.07
     Backup
    -0.06
    exceptions
    -0.06
    ूद
    -0.06
    Oops
    -0.06
    fections
    -0.06
    ixture
    -0.06
    _MEDIA
    -0.06
     Lyons
    -0.06
    POSITIVE LOGITS
    _bi
    0.06
     VX
    0.06
     WoW
    0.06
    arti
    0.06
     getting
    0.06
    	eval
    0.06
     Mur
    0.06
     Ή
    0.06
    อว
    0.06
     espera
    0.06
    Activations Density 0.001%

    No Known Activations