© 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. 15-LLAMASCOPE-RES-131K
    11. 104137
    Prev
    Next
    INDEX
    Explanations

    terms related to navigation and navigability

    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
    edException
    -0.08
    ossier
    -0.08
    utz
    -0.07
    ÑģÑĭ
    -0.07
    /fast
    -0.07
    itzer
    -0.07
    urance
    -0.07
    опаÑģ
    -0.07
    jom
    -0.07
    Æ°á»Ľi
    -0.07
    POSITIVE LOGITS
    orld
    0.07
        ↵    ↵
    0.07
    ird
    0.07
    tainment
    0.06
    antom
    0.06
    UpDown
    0.06
     Damon
    0.06
    istics
    0.06
    agation
    0.05
     Pend
    0.05
    Activations Density 0.004%

    No Known Activations