© 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. 56600
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental corridors and habitat connectivity

    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
     graves
    -0.07
    اÛĮØ´
    -0.06
    _AUX
    -0.06
     fout
    -0.06
     Mush
    -0.06
     vanity
    -0.06
    ohan
    -0.06
     Sullivan
    -0.06
    846
    -0.06
    rozen
    -0.06
    POSITIVE LOGITS
     buffers
    0.07
     across
    0.07
     Across
    0.07
     networks
    0.07
    icular
    0.07
    ursal
    0.07
     Buff
    0.06
    agal
    0.06
     movement
    0.06
     buffer
    0.06
    Activations Density 0.004%

    No Known Activations