© 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. 80212
    Prev
    Next
    INDEX
    Explanations

    references to international organizations or concepts

    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
    گاÙĩ
    -0.09
    ards
    -0.06
    ja
    -0.06
    ipay
    -0.06
    icolon
    -0.06
    824
    -0.06
    eln
    -0.06
    storm
    -0.06
    Ùĥس
    -0.06
    soever
    -0.06
    POSITIVE LOGITS
    /local
    0.10
    ization
    0.10
    izing
    0.10
    -standard
    0.10
    isation
    0.10
    ized
    0.10
    /dom
    0.09
    izes
    0.09
    ität
    0.09
    ising
    0.08
    Activations Density 0.025%

    No Known Activations