© 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. 17-LLAMASCOPE-RES-131K
    11. 129349
    Prev
    Next
    INDEX
    Explanations

    agricultural terms related to harvesting and the processes involved

    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
     norge
    -0.07
    uros
    -0.07
    acia
    -0.07
    jedn
    -0.06
     danmark
    -0.06
    anian
    -0.06
    .PrintWriter
    -0.06
    аÑĤÑĭ
    -0.06
    @if
    -0.06
     frankfurt
    -0.06
    POSITIVE LOGITS
     processing
    0.09
     collect
    0.09
    Collect
    0.08
     Processing
    0.08
    collect
    0.08
    Processing
    0.08
     collecting
    0.07
     collectors
    0.07
    processing
    0.07
     rip
    0.07
    Activations Density 0.021%

    No Known Activations