© 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. 17515
    Prev
    Next
    INDEX
    Explanations

    mentions of performances and exhibitions in various locations

    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
    uish
    -0.07
     ((((
    -0.07
    ssi
    -0.07
     Nüfus
    -0.07
    alli
    -0.07
    ioni
    -0.07
    oun
    -0.06
    lass
    -0.06
    roup
    -0.06
    rey
    -0.06
    POSITIVE LOGITS
     venues
    0.08
     halls
    0.07
    urum
    0.07
     cities
    0.07
    forums
    0.07
     festivals
    0.07
     major
    0.07
    venues
    0.06
    major
    0.06
    Repeated
    0.06
    Activations Density 0.018%

    No Known Activations