© 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. 9-LLAMASCOPE-RES-131K
    11. 96303
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions related to community and identity

    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
     пÑĢогÑĢами
    -0.07
    letters
    -0.07
    ãĥŀãĥ³
    -0.07
    zo
    -0.07
    wald
    -0.07
    vl
    -0.07
    ader
    -0.07
    ÄįnÃŃ
    -0.07
     Griffith
    -0.06
    etrofit
    -0.06
    POSITIVE LOGITS
     Packing
    0.06
    0.06
    appers
    0.06
    ué
    0.06
    IGNAL
    0.06
    oto
    0.05
    riere
    0.05
     Inbox
    0.05
    ingo
    0.05
     occur
    0.05
    Activations Density 0.340%

    No Known Activations