© 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 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. 29299
    Prev
    Next
    INDEX
    Explanations

    key phrases and significant events related to health, funding, and business-related 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
     previously
    -0.07
    EndDate
    -0.07
     Previously
    -0.07
    bens
    -0.07
    PathComponent
    -0.06
    viar
    -0.06
     poslednÃŃch
    -0.06
    tvrt
    -0.06
    anged
    -0.06
     endDate
    -0.06
    POSITIVE LOGITS
     initial
    0.26
     Initial
    0.23
    initial
    0.21
    Initial
    0.21
    åĪĿ
    0.19
     inicial
    0.19
    _initial
    0.19
    -initial
    0.18
    .initial
    0.18
     initially
    0.18
    Activations Density 0.005%

    No Known Activations