© 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. 5-LLAMASCOPE-RES-131K
    11. 125613
    Prev
    Next
    INDEX
    Explanations

    mentions of technology-related payment systems and processes

    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
     ragaz
    -0.07
    _mB
    -0.07
    adders
    -0.07
    _tF
    -0.07
    룸
    -0.07
    _mE
    -0.06
    ilot
    -0.06
    isman
    -0.06
    ounce
    -0.06
    376
    -0.06
    POSITIVE LOGITS
     diss
    0.07
    _Internal
    0.06
    weets
    0.06
    leys
    0.06
    _UL
    0.06
    imar
    0.06
    vap
    0.06
     quot
    0.05
    عار
    0.05
    VD
    0.05
    Activations Density 0.021%

    No Known Activations