© 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. 108519
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associated context

    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
    lemn
    -0.06
    ÑĪка
    -0.06
    osta
    -0.06
    ÅĻ
    -0.06
     snap
    -0.06
    ÙĪرت
    -0.06
    зн
    -0.06
    ngth
    -0.06
     Ae
    -0.06
    enne
    -0.06
    POSITIVE LOGITS
    ORIA
    0.07
    .ObjectModel
    0.07
    -prepend
    0.07
    .LENGTH
    0.07
    WithTitle
    0.07
     Propel
    0.06
    LOSS
    0.06
     Stateless
    0.06
    ï¿
    0.06
    iedo
    0.06
    Activations Density 0.016%

    No Known Activations