© 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. 125995
    Prev
    Next
    INDEX
    Explanations

    songs/albums

    np_max-act · gemini-2.0-flash

    The neuron reliably spots parts of song or track titles (i.e. tokens appearing inside quotation marks in track listings).

    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
     بده
    -0.07
    347
    -0.07
    =set
    -0.07
    易
    -0.07
    -new
    -0.07
    olik
    -0.06
     leben
    -0.06
    ")↵
    -0.06
    an
    -0.06
    ')↵
    -0.06
    POSITIVE LOGITS
    لو
    0.06
     GÜ
    0.06
    .global
    0.06
     συνέ
    0.06
    �
    0.06
     '%$
    0.06
    骑
    0.06
    _ITEM
    0.06
    arduino
    0.06
     sund
    0.06
    Activations Density 0.016%

    No Known Activations