© 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
    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. 90807
    Prev
    Next
    INDEX
    Explanations

    listen

    np_max-act · gemini-2.0-flash

    the presence of the word “listen.”

    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
    4
    -0.08
    .area
    -0.07
     Ford
    -0.07
    464
    -0.07
    5
    -0.06
    39
    -0.06
    $form
    -0.06
    ='${
    -0.06
    ?q
    -0.06
    67
    -0.06
    POSITIVE LOGITS
     listen
    0.12
     listening
    0.12
     listened
    0.12
     Listen
    0.12
    Listen
    0.11
    listen
    0.10
    listening
    0.10
    .listen
    0.10
     listens
    0.09
    _listen
    0.09
    Activations Density 0.011%

    No Known Activations