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. 85593
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron detects jQuery ID selector strings (the names inside “#…” in calls like $("#…")).

    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
    EMBER
    -0.07
     sales
    -0.07
    -sales
    -0.07
     clusters
    -0.07
    ernal
    -0.06
    holes
    -0.06
     ≤
    -0.06
     plaats
    -0.06
    ền
    -0.06
    Sales
    -0.06
    POSITIVE LOGITS
     <<↵
    0.07
    _IMG
    0.06
     deadlock
    0.06
     +++
    0.06
     Bias
    0.06
     metodo
    0.06
    мовір
    0.06
    AGMA
    0.06
    malink
    0.06
    EEEE
    0.06
    Activations Density 0.022%

    No Known Activations