© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129795
    Prev
    Next
    INDEX
    Explanations

    habit

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect mentions of “habit” and related discussion of forming or tracking new habits.

    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
     сай
    -0.07
    _linux
    -0.06
     Prevention
    -0.06
    ![↵
    -0.06
    .call
    -0.06
     Developers
    -0.06
     reputed
    -0.06
    .send
    -0.06
    .findall
    -0.06
     _('
    -0.06
    POSITIVE LOGITS
     ATM
    0.06
    ufficient
    0.06
    Ens
    0.06
    uč
    0.06
    هاي
    0.06
    BuilderFactory
    0.06
    MEDIA
    0.06
    ibern
    0.06
    .Cursors
    0.06
     quil
    0.06
    Activations Density 0.014%

    No Known Activations