© 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. 5275
    Prev
    Next
    INDEX
    Explanations

    terms related to geographic information systems (GIS) and location-based 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
    illo
    -0.06
    bjerg
    -0.06
    istrovstvÃŃ
    -0.06
    loub
    -0.06
    emple
    -0.06
    ulace
    -0.06
    ately
    -0.06
    atives
    -0.06
    -gnu
    -0.06
    енÑĤÑĥ
    -0.06
    POSITIVE LOGITS
    ergy
    0.08
    evi
    0.07
    ords
    0.07
    borne
    0.06
    PERT
    0.06
    indi
    0.06
    akis
    0.06
    etooth
    0.06
    caret
    0.06
    crease
    0.06
    Activations Density 0.022%

    No Known Activations