© 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. 85276
    Prev
    Next
    INDEX
    Explanations

    terms related to goals and positive outcomes

    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
    wyn
    -0.07
    oeff
    -0.07
    iet
    -0.06
    анÑģ
    -0.06
    imore
    -0.06
    ợi
    -0.06
    ouri
    -0.06
     spect
    -0.06
     Concepts
    -0.06
    usp
    -0.06
    POSITIVE LOGITS
    éģº
    0.07
    ugar
    0.06
    Performed
    0.06
    ä¹ħ
    0.06
    906
    0.06
    adera
    0.06
    üçük
    0.06
    .poly
    0.06
    лиÑĪ
    0.06
    .yang
    0.06
    Activations Density 0.000%

    No Known Activations