© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 802
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron responds to terms and phrases about material density and volume (e.g. “dense,” “volume,” “space,” “feathers,” “lead”) in weight‐comparison explanations.

    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
     tertiary
    -0.06
     zoals
    -0.06
     tapping
    -0.06
    uran
    -0.06
    718
    -0.06
     Ther
    -0.06
     billionaires
    -0.06
     studi
    -0.06
     cuffs
    -0.06
     sharpen
    -0.06
    POSITIVE LOGITS
     розп
    0.06
    ++){
    0.06
    收益
    0.06
     prevents
    0.06
     объем
    0.06
    提示
    0.06
    idelity
    0.06
     گیر
    0.06
     Jeremy
    0.06
     склада
    0.06
    Activations Density 0.020%

    No Known Activations