© 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. 106236
    Prev
    Next
    INDEX
    Explanations

    references to navigation and location-related activities

    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
    UME
    -0.07
    ascript
    -0.07
    ئة
    -0.07
    θμ
    -0.07
    rna
    -0.07
    ulkan
    -0.07
    $MESS
    -0.07
    annis
    -0.07
    specialchars
    -0.06
    ylon
    -0.06
    POSITIVE LOGITS
     map
    0.28
    map
    0.23
     maps
    0.23
     Map
    0.21
    -map
    0.20
    Map
    0.20
     mapa
    0.19
    (map
    0.18
     Maps
    0.18
    _map
    0.18
    Activations Density 0.068%

    No Known Activations