© 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 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. 61095
    Prev
    Next
    INDEX
    Explanations

    an emphasis on community engagement and personal aspirations

    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
    668
    -0.06
    Ñĸ
    -0.06
    sen
    -0.06
    ă
    -0.06
     Vine
    -0.05
    ANGE
    -0.05
    -&
    -0.05
    аÑħ
    -0.05
    cf
    -0.05
     conc
    -0.05
    POSITIVE LOGITS
    ieres
    0.08
    ži
    0.07
    дейÑģÑĤв
    0.07
    annels
    0.07
    Ä°Åŀ
    0.07
    curities
    0.07
    èĻŁ
    0.06
     Parenthood
    0.06
     pošk
    0.06
    reas
    0.06
    Activations Density 0.006%

    No Known Activations