© 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. 15-LLAMASCOPE-RES-131K
    11. 89380
    Prev
    Next
    INDEX
    Explanations

    punctuations and symbols used in technical descriptions

    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
    illez
    -0.08
    heimer
    -0.08
    anten
    -0.08
    urus
    -0.07
    urette
    -0.07
     suscept
    -0.07
    TriState
    -0.07
    amedi
    -0.07
    zsche
    -0.07
    obar
    -0.07
    POSITIVE LOGITS
     dav
    0.07
     Wax
    0.06
     Gent
    0.06
     Uber
    0.06
     Buff
    0.06
    Bow
    0.05
     Fol
    0.05
     correct
    0.05
    eland
    0.05
    kers
    0.05
    Activations Density 0.002%

    No Known Activations