© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 84368
    Prev
    Next
    INDEX
    Explanations

    concepts related to the idea of difference and meaning in various contexts

    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
    adera
    -0.08
    elerik
    -0.07
    eda
    -0.07
    optera
    -0.07
    aggable
    -0.07
    razil
    -0.07
    ucer
    -0.06
     Occ
    -0.06
    reds
    -0.06
    ocê
    -0.06
    POSITIVE LOGITS
    ÑĪкÑĥ
    0.07
    ardon
    0.07
     meanings
    0.07
    mean
    0.06
    kins
    0.06
    (mean
    0.06
     Mean
    0.06
     mean
    0.06
    vm
    0.06
     Chance
    0.06
    Activations Density 0.019%

    No Known Activations