© 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. 57762
    Prev
    Next
    INDEX
    Explanations

    terms related to geological processes and formations

    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
     metic
    -0.07
     заг
    -0.06
    енÑı
    -0.06
    pod
    -0.06
    åħ¨åĽ½
    -0.06
    âĢĤ
    -0.06
     equiv
    -0.06
    jar
    -0.05
     Frequently
    -0.05
     Rack
    -0.05
    POSITIVE LOGITS
    ojis
    0.09
    nty
    0.07
    itura
    0.07
    ijd
    0.07
    escort
    0.07
     éĻIJ
    0.07
     defaultManager
    0.07
    ª
    0.07
    inded
    0.07
    ersed
    0.07
    Activations Density 0.005%

    No Known Activations