© 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. 54842
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering and infrastructure

    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
    gate
    -0.07
    opr
    -0.07
    OffsetTable
    -0.06
    urai
    -0.06
    ãĥ¼ãĥĬ
    -0.06
    .IContainer
    -0.06
     éķ
    -0.06
    Assembly
    -0.06
    uo
    -0.06
    KM
    -0.06
    POSITIVE LOGITS
    859
    0.07
    TextColor
    0.07
    .isEnabled
    0.06
    ~~~~
    0.06
    .openg
    0.06
     isolation
    0.06
    rophe
    0.06
     ÑģкÑĢÑĭ
    0.06
    756
    0.06
    swire
    0.06
    Activations Density 0.014%

    No Known Activations