© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58567
    Prev
    Next
    INDEX
    Explanations

    Warm

    np_max-act · gemini-2.0-flash

    the neuron responds to numeric tokens or numeric expressions (e.g. parts of numbers, measurements, or time values)

    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
    ー�
    -0.07
    IsActive
    -0.07
     Ion
    -0.06
     soruml
    -0.06
    ))
    -0.06
    ungeons
    -0.06
    βι
    -0.06
    ))):↵
    -0.06
    )):↵
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     crem
    0.07
     кис
    0.07
     ReactiveFormsModule
    0.06
     transporting
    0.06
    THREAD
    0.06
     kurz
    0.06
     staple
    0.06
     Administrator
    0.06
    (headers
    0.06
    (HttpStatusCode
    0.06
    Activations Density 0.141%

    No Known Activations