© 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. 107906
    Prev
    Next
    INDEX
    Explanations

    assertions about collective experiences or beliefs

    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
    _THRESH
    -0.08
     Excell
    -0.07
    æīķ
    -0.07
     наÑģÑĤ
    -0.07
    SED
    -0.07
    agues
    -0.07
    -Cs
    -0.06
    ä¸ĺ
    -0.06
     myself
    -0.06
    ÃŃna
    -0.06
    POSITIVE LOGITS
    ensa
    0.07
    ipe
    0.07
     mutually
    0.07
     Adler
    0.07
    uld
    0.07
    iju
    0.06
    kker
    0.06
    154
    0.06
    ibu
    0.06
    UDO
    0.06
    Activations Density 0.056%

    No Known Activations