© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 82172
    Prev
    Next
    INDEX
    Explanations

    technical references to mathematical concepts and their applications within scientific contexts

    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
    ropolis
    -0.07
    ikat
    -0.07
    lev
    -0.07
    legation
    -0.07
    _tA
    -0.06
    ispers
    -0.06
    кÑĸв
    -0.06
    inson
    -0.06
    catid
    -0.06
    æĭ©
    -0.06
    POSITIVE LOGITS
    umpy
    0.07
     presence
    0.07
    oods
    0.06
     abs
    0.06
    onis
    0.06
    anner
    0.06
    presence
    0.06
    598
    0.06
     absence
    0.06
     pres
    0.06
    Activations Density 0.098%

    No Known Activations