© 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. 58996
    Prev
    Next
    INDEX
    Explanations

    enumerations and structured lists within the text

    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
    eln
    -0.07
    DAC
    -0.07
    ropp
    -0.06
    ãģıãĤī
    -0.06
    και
    -0.06
    oint
    -0.06
    abay
    -0.06
    aren
    -0.06
    Stencil
    -0.06
    ég
    -0.06
    POSITIVE LOGITS
    reation
    0.08
    erval
    0.07
    eneric
    0.06
    annels
    0.06
    soever
    0.06
    onian
    0.06
    ensburg
    0.06
    riday
    0.06
     vern
    0.06
    imary
    0.06
    Activations Density 0.024%

    No Known Activations