© 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. 9-LLAMASCOPE-RES-131K
    11. 98200
    Prev
    Next
    INDEX
    Explanations

    occurrences of repetitive actions and detailed explanations

    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
    ØŃÙĩ
    -0.07
    ammad
    -0.06
    eon
    -0.06
    .netbeans
    -0.06
    tail
    -0.06
    687
    -0.06
    uju
    -0.06
    hud
    -0.06
    hod
    -0.06
     Apost
    -0.06
    POSITIVE LOGITS
    adir
    0.07
    edia
    0.06
    ÛĮÙħ
    0.06
    _wr
    0.06
    heap
    0.06
    este
    0.06
    kek
    0.06
    appers
    0.06
    Heap
    0.06
     Bott
    0.05
    Activations Density 0.007%

    No Known Activations