© 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. 88944
    Prev
    Next
    INDEX
    Explanations

    references to conservation plans and related policies

    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
    åĬ¡
    -0.06
    ModifiedDate
    -0.06
    orca
    -0.06
    _pb
    -0.06
    RAND
    -0.05
    oš
    -0.05
    auc
    -0.05
    otos
    -0.05
     autoc
    -0.05
    ÙģÙĦ
    -0.05
    POSITIVE LOGITS
    orest
    0.07
     entitled
    0.07
    بÙĪد
    0.07
    ượng
    0.07
    æĹ
    0.06
     searchData
    0.06
    egas
    0.06
    827
    0.06
    .tt
    0.06
     RTE
    0.06
    Activations Density 0.016%

    No Known Activations