© 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. 28001
    Prev
    Next
    INDEX
    Explanations

    spatial relationships and locations within a description

    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
    öt
    -0.07
    anyl
    -0.06
     chalk
    -0.06
    ugas
    -0.06
    /spec
    -0.06
    isel
    -0.06
    isto
    -0.06
    ExceptionHandler
    -0.06
    sip
    -0.06
     queued
    -0.06
    POSITIVE LOGITS
    styled
    0.06
    ä¸
    0.06
     dep
    0.06
     lower
    0.06
    umblr
    0.06
    lož
    0.06
    Ctr
    0.06
     basement
    0.05
    esktop
    0.05
     separate
    0.05
    Activations Density 0.026%

    No Known Activations