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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 127508
    Prev
    Next
    INDEX
    Explanations

    Todo

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the token “todo” (e.g. in variable, type, or identifier 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
     spray
    -0.07
    .BASELINE
    -0.06
     Sh
    -0.06
     elbows
    -0.06
     GameController
    -0.06
     elbow
    -0.06
     lever
    -0.06
    Raised
    -0.06
     Hak
    -0.06
     EN
    -0.06
    POSITIVE LOGITS
    todo
    0.11
     Todo
    0.10
    Todo
    0.10
    .todo
    0.10
     todo
    0.09
    /todo
    0.09
     TODO
    0.08
     orthogonal
    0.08
    todos
    0.08
    (todo
    0.07
    Activations Density 0.004%

    No Known Activations