© 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. 17-LLAMASCOPE-RES-131K
    6. 127820
    Prev
    Next
    INDEX
    Explanations

    references to digital marketing metrics and traffic analysis

    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
    quete
    -0.07
     Bucc
    -0.06
    onth
    -0.06
    RSS
    -0.06
     Cho
    -0.06
     localVar
    -0.06
     Morav
    -0.06
    anio
    -0.06
    icina
    -0.06
    cho
    -0.06
    POSITIVE LOGITS
    net
    0.07
     cost
    0.07
     Cost
    0.07
    ource
    0.07
     costly
    0.07
     conversion
    0.07
    -cost
    0.07
    esso
    0.07
     Conversion
    0.06
    Cost
    0.06
    Activations Density 0.008%

    No Known Activations