© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43294
    Prev
    Next
    INDEX
    Explanations

    Capacitors

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “capacit-” (e.g. capacitor, capacitance) terms.

    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
    MainFrame
    -0.07
    とも
    -0.07
    .DAY
    -0.06
    aser
    -0.06
    混
    -0.06
     IntPtr
    -0.06
    となり
    -0.06
    etics
    -0.06
     hobby
    -0.06
    ард
    -0.06
    POSITIVE LOGITS
    iciencies
    0.08
     slash
    0.07
    iciency
    0.07
     //!
    0.07
    abilité
    0.06
    PDOException
    0.06
    Appe
    0.06
     *</
    0.06
     perso
    0.06
    .CR
    0.06
    Activations Density 0.006%

    No Known Activations