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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 671
    Prev
    Next
    INDEX
    Explanations

    missing

    np_max-act · gemini-2.0-flash

    The neuron fires on the user’s “something I’m missing” question phrase, i.e. when the post includes “Is there something I’m missing…?”

    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
    CSR
    -0.06
    ennai
    -0.06
     Lod
    -0.06
    eous
    -0.06
    Pakistan
    -0.06
     Saturday
    -0.06
    opcode
    -0.06
     Crushing
    -0.06
    必
    -0.06
     Aid
    -0.05
    POSITIVE LOGITS
    .build
    0.07
    .Pop
    0.07
    ание
    0.06
    %;">
    0.06
    　イ
    0.06
    .exc
    0.06
     М
    0.06
     physicists
    0.06
     notebook
    0.06
     />;↵
    0.06
    Activations Density 0.011%

    No Known Activations