© 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. 109449
    Prev
    Next
    INDEX
    Explanations

    spectral

    np_max-act · gemini-2.0-flash

    This neuron activates on technical mathematical terms related to spectra (eigenvalues, spectral radius, Laplacian spectrum) in academic or graph‐theoretic contexts.

    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
    レ
    -0.06
     violin
    -0.06
    .binary
    -0.06
     larvae
    -0.06
     confronting
    -0.06
    externalActionCode
    -0.06
    หลาย
    -0.06
     OBS
    -0.06
     chewing
    -0.06
    绩
    -0.06
    POSITIVE LOGITS
    akter
    0.08
     Sunder
    0.08
     relentlessly
    0.07
     campaign
    0.07
     assure
    0.07
    _hw
    0.06
     ble
    0.06
    muz
    0.06
    -dis
    0.06
    .turn
    0.06
    Activations Density 0.006%

    No Known Activations