© 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. 55518
    Prev
    Next
    INDEX
    Explanations

    musical style

    np_max-act · gemini-2.0-flash

    The neuron activates on language describing a shift or change in musical style or direction.

    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
    _router
    -0.08
    -read
    -0.07
     contradictory
    -0.07
    (login
    -0.07
     def
    -0.07
     Josh
    -0.06
     imgs
    -0.06
    _height
    -0.06
    чит
    -0.06
    izers
    -0.06
    POSITIVE LOGITS
     bíl
    0.07
    üml
    0.07
     đỏ
    0.06
     ऑ
    0.06
    ">',↵
    0.06
    uyên
    0.06
    <>
    0.06
    .General
    0.06
    ヨ
    0.06
    reon
    0.06
    Activations Density 0.064%

    No Known Activations