© 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. 1503
    Prev
    Next
    INDEX
    Explanations

    occurrences of arrival or presence in various 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
    htub
    -0.08
    inely
    -0.07
    _FM
    -0.07
    ovo
    -0.07
    erras
    -0.07
    μί
    -0.07
    avanaugh
    -0.07
    ãģªãģĮ
    -0.07
    ASP
    -0.06
    xl
    -0.06
    POSITIVE LOGITS
     arrival
    0.08
     Arrival
    0.07
    ery
    0.07
     arrived
    0.07
     late
    0.07
     arrivals
    0.07
     arrive
    0.07
    onta
    0.07
     via
    0.06
     arriv
    0.06
    Activations Density 0.042%

    No Known Activations