© 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 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. 88382
    Prev
    Next
    INDEX
    Explanations

    structural elements in a JSON format

    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
    âĢ¦
    -0.09
    -↵
    -0.07
    int
    -0.07
    str
    -0.06
    ynes
    -0.06
    the
    -0.06
    chlor
    -0.06
    esseract
    -0.06
    .yang
    -0.06
    ox
    -0.06
    POSITIVE LOGITS
    ity
    0.08
    reesome
    0.08
    er
    0.07
    amera
    0.07
    omite
    0.07
    ÛĮ
    0.07
    untu
    0.07
    ำ
    0.07
    ãĥ¥
    0.06
    ndo
    0.06
    Activations Density 0.056%

    No Known Activations