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. 128956
    Prev
    Next
    INDEX
    Explanations

    Supremum notation

    np_max-act · gemini-2.0-flash

    This neuron fires on LaTeX‐style functional‐analysis notation—especially names of function spaces (e.g. C, L∞, W²,φ) and their norms.

    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
    ΟΝ
    -0.07
    _HOST
    -0.07
    /chat
    -0.07
    /Search
    -0.07
    icles
    -0.07
    -Regular
    -0.06
     Lost
    -0.06
    Dragging
    -0.06
     scoop
    -0.06
    PB
    -0.06
    POSITIVE LOGITS
    "".
    0.07
    ubern
    0.07
     encontrado
    0.06
     ků
    0.06
    earable
    0.06
    _configs
    0.06
    lut
    0.06
     the
    0.06
     起
    0.06
     inferior
    0.06
    Activations Density 0.002%

    No Known Activations