© 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. 29136
    Prev
    Next
    INDEX
    Explanations

    references to locations or spatial relationships

    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
    ÂłPS
    -0.08
    ｡
    -0.07
    ichi
    -0.07
    geh
    -0.07
    eyin
    -0.07
    tuÄŁ
    -0.07
    ,...↵↵
    -0.07
    GGLE
    -0.07
     abdom
    -0.07
     poil
    -0.07
    POSITIVE LOGITS
    637
    0.07
    usch
    0.07
     other
    0.07
     Pixels
    0.07
     everywhere
    0.06
    249
    0.06
     different
    0.06
     both
    0.06
    687
    0.06
    itan
    0.06
    Activations Density 0.073%

    No Known Activations