© 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. 110271
    Prev
    Next
    INDEX
    Explanations

    Technology and materials science

    np_max-act · gemini-2.0-flash

    This neuron detects technical terms related to data storage media (e.g., “magnetic,” “recording,” “media,” “beam,” “diffraction”).

    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
     override
    -0.06
    .Dimension
    -0.06
     Groups
    -0.06
    .struts
    -0.06
    Đối
    -0.06
     dub
    -0.06
     ilişk
    -0.06
     Magn
    -0.06
     initi
    -0.06
    Initialization
    -0.06
    POSITIVE LOGITS
    ями
    0.07
     ред
    0.07
    操
    0.06
    Fecha
    0.06
    _subplot
    0.06
     [&](
    0.06
                    ↵↵
    0.06
     breathing
    0.06
    .modelo
    0.06
            ↵↵
    0.06
    Activations Density 0.087%

    No Known Activations