© 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. 31059
    Prev
    Next
    INDEX
    Explanations

    technical terms related to file handling and database operations

    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
    ouns
    -0.07
    alone
    -0.06
    metis
    -0.06
    igy
    -0.06
    hf
    -0.06
    akan
    -0.06
    ropa
    -0.06
    اÙĨÛĮ
    -0.06
    lingen
    -0.06
     pap
    -0.06
    POSITIVE LOGITS
    ãĥ£
    0.07
    rosse
    0.07
    wick
    0.07
    osten
    0.07
    .cwd
    0.06
    ipi
    0.06
    ez
    0.06
    IFA
    0.06
    .Exists
    0.06
    et
    0.06
    Activations Density 0.000%

    No Known Activations