Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 110068
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    np_max-act · gemini-2.0-flash

    The neuron fires on the start of descriptive sentences about books—particularly around the word “book” when it’s followed by phrases like “provides.”

    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
     Borough
    -0.07
    елів
    -0.07
    :description
    -0.06
    groupid
    -0.06
    ."&
    -0.06
    .pkl
    -0.06
    Directed
    -0.06
     forCellReuseIdentifier
    -0.06
     فران
    -0.06
    :h
    -0.06
    POSITIVE LOGITS
     theat
    0.07
    .viewModel
    0.07
     книги
    0.06
     shirt
    0.06
    emat
    0.06
     miscar
    0.06
    /XML
    0.06
     admon
    0.06
     unreliable
    0.06
    (Attribute
    0.06
    Activations Density 0.021%

    No Known Activations