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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7262
    Prev
    Next
    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash

    The neuron activates on placeholder name tokens (e.g. “NAME_1,” “NAME_2,” etc.), i.e. tokens representing character names.

    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
    ็ต
    -0.07
    脂
    -0.07
     SWT
    -0.07
     Newtown
    -0.07
     yapılmış
    -0.06
    ctrl
    -0.06
     téc
    -0.06
    getState
    -0.06
    Ten
    -0.06
    tl
    -0.06
    POSITIVE LOGITS
     cropping
    0.06
    .success
    0.06
    　　　 　 　 　
    0.06
     sketches
    0.06
    _ax
    0.06
    кую
    0.06
     Michael
    0.06
     ander
    0.06
     infinity
    0.06
     〉
    0.05
    Activations Density 0.031%

    No Known Activations