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. 6666
    Prev
    Next
    INDEX
    Explanations

    doubles

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of baseball performance statistics and related action terms (e.g. throwing, catching, stolen bases).

    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
    ology
    -0.07
    .backends
    -0.06
    Base
    -0.06
    average
    -0.06
     Lin
    -0.06
    figures
    -0.06
    (pow
    -0.06
     цар
    -0.06
    loi
    -0.06
     Ease
    -0.06
    POSITIVE LOGITS
     символ
    0.06
     κορ
    0.06
    EHICLE
    0.06
    obic
    0.06
     Authentication
    0.06
     вмест
    0.06
     snug
    0.06
     wanting
    0.06
     THEY
    0.06
    ........
    0.06
    Activations Density 0.011%

    No Known Activations