© 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. 118217
    Prev
    Next
    INDEX
    Explanations

    references to watersheds and related environmental issues

    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
    abeth
    -0.08
    cie
    -0.07
    CEE
    -0.07
    zell
    -0.07
    anton
    -0.07
    zel
    -0.07
    aign
    -0.07
    ãĥĨãĥ«
    -0.07
    sı
    -0.07
    jišť
    -0.06
    POSITIVE LOGITS
    -wide
    0.09
    inary
    0.07
     area
    0.07
    wide
    0.07
    hed
    0.06
    oss
    0.06
    257
    0.06
    ential
    0.06
    éĻħ
    0.06
    -based
    0.06
    Activations Density 0.007%

    No Known Activations