© 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. 25038
    Prev
    Next
    INDEX
    Explanations

    plans

    np_max-act · gemini-2.0-flash

    The neuron lights up on words that signal plotting or scheming (e.g. “plan,” “plot,” “hatch,” “scheme”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    historical events related to plans and conspiracies involving nobility.

    oai_token-act-pair · gpt-4o-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
     Ambassador
    -0.08
    ovaly
    -0.07
    .DialogResult
    -0.06
     });
↵
↵
    -0.06
     页面
    -0.06
    /logs
    -0.06
    ();
↵
↵
    -0.06
     ambassador
    -0.06
     insects
    -0.06
    .Validation
    -0.06
    POSITIVE LOGITS
     plans
    0.09
     laundering
    0.08
     plan
    0.08
     бел
    0.07
     BIG
    0.07
     нес
    0.07
    LOT
    0.06
     Northwestern
    0.06
     toolbox
    0.06
     schem
    0.06
    Activations Density 0.031%

    No Known Activations