© 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. 9295
    Prev
    Next
    INDEX
    Explanations

    recommendations or suggestions

    np_max-act · gemini-2.0-flash

    The neuron activates on phrases that express a warning or discourage a suggested action (e.g., “not a good idea,” “not recommended,” “not advisable”).

    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
     Archbishop
    -0.07
    stoff
    -0.07
     сили
    -0.07
     doctoral
    -0.07
    Hp
    -0.06
    (P
    -0.06
    EditMode
    -0.06
     eskorte
    -0.06
     Nug
    -0.06
    HeadersHeight
    -0.06
    POSITIVE LOGITS
    ọ
    0.07
    -wise
    0.06
    omed
    0.06
    下去
    0.06
    =models
    0.06
     ill
    0.06
     imposed
    0.06
    丈夫
    0.06
     stos
    0.06
     barang
    0.06
    Activations Density 0.019%

    No Known Activations