© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 129946
    Prev
    Next
    INDEX
    Explanations

    open spaces

    np_max-act · gemini-2.0-flash

    The neuron flags descriptive terms for broad, open natural landscapes (e.g. “rolling,” “hills,” “endless expanse,” “desert,” “sea”).

    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
     března
    -0.06
    Silver
    -0.06
    .environ
    -0.06
    _al
    -0.06
     enrich
    -0.06
     disguise
    -0.06
    GBP
    -0.06
     militants
    -0.06
    amba
    -0.06
    卢
    -0.06
    POSITIVE LOGITS
     Enumerable
    0.06
    .visualization
    0.06
    _CLIENT
    0.06
    Downloads
    0.06
    [opt
    0.06
    rax
    0.06
    Advertisements
    0.06
    Λ
    0.06
    |wx
    0.06
    rof
    0.06
    Activations Density 0.021%

    No Known Activations