© 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. 17-LLAMASCOPE-RES-131K
    11. 85542
    Prev
    Next
    INDEX
    Explanations

    references to procedures or methods in various contexts

    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
    tember
    -0.07
    itez
    -0.07
    ji
    -0.07
    foon
    -0.06
    xn
    -0.06
    lsen
    -0.06
    cks
    -0.06
    venes
    -0.06
    że
    -0.06
    neas
    -0.06
    POSITIVE LOGITS
    ional
    0.10
    /process
    0.08
    ions
    0.08
    -process
    0.07
    icular
    0.07
     itself
    0.07
    ivity
    0.07
    ually
    0.07
    ual
    0.07
    ioned
    0.07
    Activations Density 0.023%

    No Known Activations