© 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. 15-LLAMASCOPE-RES-131K
    11. 88815
    Prev
    Next
    INDEX
    Explanations

    references to registration processes and interactions between users and systems

    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
    ivec
    -0.06
    avec
    -0.06
    iss
    -0.06
     ”↵↵
    -0.06
    andle
    -0.06
    isini
    -0.06
    coe
    -0.06
    rst
    -0.06
    squ
    -0.06
    amik
    -0.06
    POSITIVE LOGITS
    uger
    0.07
    olland
    0.07
    Immutable
    0.07
    ryptography
    0.07
    nap
    0.07
    igma
    0.06
    Ñĸнки
    0.06
    ¢åįķ
    0.06
    'er
    0.06
    eries
    0.06
    Activations Density 0.007%

    No Known Activations