© 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. 42657
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron is detecting code‐block delimiters (the backtick sequences that mark start/end of code snippets).

    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
     tuổi
    -0.07
     sewage
    -0.06
    ertiary
    -0.06
    (xpath
    -0.06
    .assertAlmostEqual
    -0.06
     Dolphin
    -0.06
     charcoal
    -0.06
     pudd
    -0.06
    ül
    -0.06
    (Job
    -0.06
    POSITIVE LOGITS
    _Left
    0.07
    _backend
    0.07
    _LD
    0.07
    "(
    0.07
    -vs
    0.06
     політи
    0.06
     senza
    0.06
    outcome
    0.06
    came
    0.06
    Outlined
    0.06
    Activations Density 0.022%

    No Known Activations