© 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. 5398
    Prev
    Next
    INDEX
    Explanations

    terms related to comprehensive service offerings in various industries

    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
    ndon
    -0.07
    culus
    -0.07
    arty
    -0.07
    ewater
    -0.07
    stor
    -0.07
    atedRoute
    -0.06
    /her
    -0.06
     updatedAt
    -0.06
     xuyên
    -0.06
    (æ°´
    -0.06
    POSITIVE LOGITS
    ery
    0.07
     solution
    0.07
     solutions
    0.07
    olutions
    0.07
    isu
    0.07
     Lös
    0.06
    icity
    0.06
    solution
    0.06
    urance
    0.06
     facility
    0.06
    Activations Density 0.005%

    No Known Activations