© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87862
    Prev
    Next
    INDEX
    Explanations

    terms related to rules, regulations, and governance

    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
    avax
    -0.07
    ///<
    -0.06
    ucs
    -0.06
    łģ
    -0.06
    boa
    -0.06
     Shield
    -0.06
    ÙħÛĮÙĨ
    -0.06
    avou
    -0.06
    yonel
    -0.06
    GI
    -0.06
    POSITIVE LOGITS
     published
    0.08
    heets
    0.06
    arkin
    0.06
    htable
    0.06
    NDAR
    0.06
    heet
    0.06
    appen
    0.06
     Rub
    0.06
     Conway
    0.06
    APSHOT
    0.06
    Activations Density 0.027%

    No Known Activations