© 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. 75043
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate breadth or range of concepts

    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
    kinson
    -0.07
     Tradable
    -0.07
    çļ
    -0.07
    ffen
    -0.07
    лив
    -0.06
    avra
    -0.06
     Chandler
    -0.06
    iddet
    -0.06
     shin
    -0.06
    γÏĩ
    -0.06
    POSITIVE LOGITS
    èĮĥåĽ´
    0.13
     range
    0.12
     scope
    0.12
     coverage
    0.11
    coverage
    0.10
    -ranging
    0.10
    -range
    0.10
     spectrum
    0.10
     scopes
    0.09
    -wide
    0.09
    Activations Density 0.038%

    No Known Activations