© 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. 130817
    Prev
    Next
    INDEX
    Explanations

    locations and geographical descriptions

    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
    ardy
    -0.07
    aylight
    -0.07
    odge
    -0.07
    enk
    -0.07
    //{{
    -0.06
     grátis
    -0.06
    CCCC
    -0.06
    .SEVER
    -0.06
     cigaret
    -0.06
    аÑĢа
    -0.06
    POSITIVE LOGITS
     conver
    0.07
    ãĥ«ãĥī
    0.06
     cro
    0.06
     decl
    0.06
     convergence
    0.06
     Located
    0.06
    pekt
    0.06
     Carpenter
    0.06
    ylko
    0.06
    mn
    0.06
    Activations Density 0.039%

    No Known Activations