© 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. 9-LLAMASCOPE-RES-131K
    11. 98708
    Prev
    Next
    INDEX
    Explanations

    terms related to the management and control of service animals

    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
    sei
    -0.08
    thon
    -0.08
    beth
    -0.07
    ãĥ¼ãĥijãĥ¼
    -0.07
    impan
    -0.07
    imento
    -0.06
    isé
    -0.06
    fusion
    -0.06
    inium
    -0.06
    ius
    -0.06
    POSITIVE LOGITS
    arte
    0.07
    é±
    0.07
    atr
    0.07
    odu
    0.06
    AndPassword
    0.06
    ACP
    0.06
    ambia
    0.06
    ÅĻÃŃd
    0.05
    744
    0.05
    åŁ
    0.05
    Activations Density 0.003%

    No Known Activations