© 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. 127970
    Prev
    Next
    INDEX
    Explanations

    narrative elements related to personal and collective experiences

    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
    izando
    -0.07
    δα
    -0.07
    ½Ķ
    -0.07
    NAMESPACE
    -0.07
    angler
    -0.06
    ecta
    -0.06
    acos
    -0.06
    sburg
    -0.06
    icted
    -0.06
    =forms
    -0.06
    POSITIVE LOGITS
    swire
    0.07
    ÑĢÑĥÑĪ
    0.06
    olume
    0.06
     Liberation
    0.06
    keleton
    0.06
     Gaines
    0.06
    voj
    0.06
    ï¿
    0.06
    gles
    0.06
    ész
    0.06
    Activations Density 0.028%

    No Known Activations