© 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. 3091
    Prev
    Next
    INDEX
    Explanations

    terms related to product effectiveness and approval

    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
    unic
    -0.06
     Mas
    -0.06
    cak
    -0.06
    eson
    -0.06
    aine
    -0.06
    esan
    -0.06
    se
    -0.06
    idas
    -0.06
    iane
    -0.06
    ylon
    -0.05
    POSITIVE LOGITS
    NECT
    0.07
    ê´Ģ
    0.07
    CppType
    0.07
    kili
    0.07
    é³
    0.07
    cano
    0.07
    ümÃ¼ÅŁ
    0.07
    زÙĦ
    0.07
    leurs
    0.07
    _("
    0.06
    Activations Density 0.002%

    No Known Activations