© 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. 95667
    Prev
    Next
    INDEX
    Explanations

    concepts related to optimization and querying 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
    caffold
    -0.07
    _initializer
    -0.07
    leftright
    -0.07
    aupt
    -0.07
    adık
    -0.07
    elligence
    -0.07
    ænd
    -0.07
    ÏĦια
    -0.07
    aison
    -0.06
    -mf
    -0.06
    POSITIVE LOGITS
     motivational
    0.06
     worst
    0.06
     Worst
    0.06
    DRAM
    0.06
     mort
    0.06
    erton
    0.06
    dur
    0.06
     divorced
    0.06
    ÏģοÏħ
    0.06
     spilled
    0.06
    Activations Density 0.006%

    No Known Activations