© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 132
    Prev
    Next
    INDEX
    Explanations

    references to statistical methods and concepts

    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
    sworth
    -0.08
    ahren
    -0.07
    _datos
    -0.07
    tings
    -0.07
    çĽijåIJ¬é¡µéĿ¢
    -0.07
    eft
    -0.06
    pel
    -0.06
     é¤
    -0.06
    è¾ij
    -0.06
    گاÙĩ
    -0.06
    POSITIVE LOGITS
    istical
    0.10
    istically
    0.09
     quo
    0.09
    itics
    0.08
    utory
    0.08
     minded
    0.07
    cly
    0.07
    emachine
    0.07
    ellite
    0.07
    vfs
    0.07
    Activations Density 0.025%

    No Known Activations