© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68476
    Prev
    Next
    INDEX
    Explanations

    bug

    np_max-act · gemini-2.0-flash

    The neuron responds to references to bug-tracking URLs or IDs (e.g. “bugzilla.org/show_bug.cgi?id=123456”).

    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
    _FRE
    -0.07
    -La
    -0.07
    毛
    -0.06
    605
    -0.06
    �
    -0.06
    tre
    -0.06
     ακό
    -0.06
    _SUB
    -0.06
    ndl
    -0.06
    (lp
    -0.06
    POSITIVE LOGITS
    または
    0.07
     Seahawks
    0.06
     amendments
    0.06
    环境
    0.06
     Intercept
    0.06
    -xl
    0.06
     Alerts
    0.06
     Zealand
    0.06
    .setState
    0.06
     граду
    0.06
    Activations Density 0.000%

    No Known Activations