© 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. 68911
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron activates on C‐style preprocessor macro lines (e.g. “#define” and the all‐caps identifiers that follow).

    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
    displayName
    -0.07
    .nextInt
    -0.06
    دار
    -0.06
    VI
    -0.06
    kân
    -0.06
    .green
    -0.06
    SequentialGroup
    -0.06
     Nar
    -0.06
     coco
    -0.06
    Ultra
    -0.06
    POSITIVE LOGITS
    TIME
    0.07
     полити
    0.06
    .Fatal
    0.06
     yönet
    0.06
     velké
    0.06
     marrow
    0.06
     Ledger
    0.06
    pción
    0.06
     poskyt
    0.06
    прав
    0.06
    Activations Density 0.097%

    No Known Activations