© 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. 85806
    Prev
    Next
    INDEX
    Explanations

    descriptions of streets and pathways

    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
    antium
    -0.07
    üns
    -0.07
    agedList
    -0.06
    shed
    -0.06
    hek
    -0.06
    erland
    -0.06
    owering
    -0.06
    ifo
    -0.06
    oliday
    -0.06
     banka
    -0.06
    POSITIVE LOGITS
     streets
    0.12
     street
    0.10
     alle
    0.09
     Streets
    0.09
     Street
    0.09
     alley
    0.08
    Street
    0.08
     STREET
    0.08
    street
    0.07
    bedo
    0.07
    Activations Density 0.010%

    No Known Activations