© 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. 83386
    Prev
    Next
    INDEX
    Explanations

    terms related to software or tools for troubleshooting and installation processes

    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
    eph
    -0.07
    ebek
    -0.07
    swire
    -0.07
    302
    -0.07
    baugh
    -0.07
    eti
    -0.06
    ardash
    -0.06
    ored
    -0.06
    earer
    -0.06
    flater
    -0.06
    POSITIVE LOGITS
    tro
    0.06
     Tro
    0.06
    tol
    0.06
     Hoy
    0.06
    'order
    0.06
     Serializable
    0.06
    лиÑĩ
    0.06
     tolerance
    0.06
    jac
    0.06
     Chapman
    0.06
    Activations Density 0.001%

    No Known Activations