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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39091
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    greatest hits albums and compilations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is detecting mentions of compilation or greatest‐hits album titles (e.g. “Best of,” “Greatest Hits,” “Very Best of”).

    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
     adultery
    -0.07
    I
    -0.06
     loro
    -0.06
     هفته
    -0.06
    	Port
    -0.06
     edge
    -0.06
     fiction
    -0.06
     زی
    -0.06
    })↵↵↵
    -0.06
     homemade
    -0.06
    POSITIVE LOGITS
    ＋
    0.07
    _ALIGN
    0.07
    atı
    0.07
     tématu
    0.06
     Petroleum
    0.06
     regul
    0.06
     ấn
    0.06
     Crab
    0.06
    _des
    0.06
    .Rem
    0.06
    Activations Density 0.009%

    No Known Activations