© 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. 42357
    Prev
    Next
    INDEX
    Explanations

    location-based administrative divisions or units in a geographical context

    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
    amarin
    -0.07
    loor
    -0.07
    ¬ģ
    -0.07
     палÑĮ
    -0.07
     колÑĮ
    -0.06
    .Manifest
    -0.06
    Ctr
    -0.06
    åģ
    -0.06
    untime
    -0.06
    olley
    -0.06
    POSITIVE LOGITS
     Census
    0.07
     Ple
    0.06
    sg
    0.06
     gene
    0.06
    Suppress
    0.06
    nnen
    0.06
     fich
    0.06
    Extent
    0.06
     Gene
    0.06
     gaz
    0.06
    Activations Density 0.029%

    No Known Activations