© 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. 2378
    Prev
    Next
    INDEX
    Explanations

    possessive forms indicating ownership or association

    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
    ä¸Ģä¸ĭ
    -0.06
     à¤īसन
    -0.06
     jub
    -0.06
    óng
    -0.05
    IDEO
    -0.05
    å¥
    -0.05
    çļĦæĺ¯
    -0.05
    ijo
    -0.05
    ductive
    -0.05
    upertino
    -0.05
    POSITIVE LOGITS
    chant
    0.07
    ustum
    0.07
    زÙĩ
    0.07
    uur
    0.07
    iller
    0.07
    важа
    0.06
    raison
    0.06
    omor
    0.06
    akov
    0.06
    yte
    0.06
    Activations Density 0.013%

    No Known Activations