© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 93895
    Prev
    Next
    INDEX
    Explanations

    terms related to family relationships and parental figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ³ãĤ¬
    -0.09
    hores
    -0.07
    åĽ½äº§
    -0.07
    ìĶ
    -0.07
    plementation
    -0.07
    اسÙĩ
    -0.07
    _WM
    -0.07
     Sesso
    -0.07
    mainwindow
    -0.07
    omens
    -0.07
    POSITIVE LOGITS
     merc
    0.06
    oes
    0.06
    tern
    0.06
     gone
    0.06
    hood
    0.06
    irit
    0.06
    -da
    0.06
    zac
    0.05
    CF
    0.05
    erial
    0.05
    Activations Density 0.011%

    No Known Activations