© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 105585
    Prev
    Next
    INDEX
    Explanations

    mentions of specific female names, particularly variations of "Tina" and "Nina."

    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
    اÙħÙĦ
    -0.08
    802
    -0.08
    agrams
    -0.07
    ught
    -0.07
    IFORM
    -0.07
     CONSEQUENTIAL
    -0.07
    åħ¥ãĤĮ
    -0.07
    $MESS
    -0.07
    ilet
    -0.07
    avn
    -0.07
    POSITIVE LOGITS
    o
    0.07
    de
    0.07
    arity
    0.07
    xis
    0.06
    éĥİ
    0.06
    elist
    0.06
    ÑĮи
    0.06
    c
    0.06
    y
    0.06
     tops
    0.06
    Activations Density 0.017%

    No Known Activations