© 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. 62582
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific qualifiers related to categories or classifications in structured data

    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
    VML
    -0.08
     Qgs
    -0.07
    ensitivity
    -0.07
    ãĥ³ãĥĸ
    -0.07
    QL
    -0.07
     decades
    -0.07
     years
    -0.07
    EventArgs
    -0.06
    finity
    -0.06
    ExecutionContext
    -0.06
    POSITIVE LOGITS
    .undefined
    0.07
    ft
    0.07
     обла
    0.06
     seniors
    0.06
    imir
    0.06
    rait
    0.06
    ÑĤÑĢо
    0.06
     aute
    0.06
    elter
    0.05
     deliver
    0.05
    Activations Density 0.000%

    No Known Activations