© 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. 28436
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration and leadership responsibilities

    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
    ngr
    -0.07
    æ²¢
    -0.07
    _Tick
    -0.07
    üre
    -0.06
    inas
    -0.06
     Griffith
    -0.06
    aight
    -0.06
    á»įt
    -0.06
    ersistence
    -0.06
    _hosts
    -0.06
    POSITIVE LOGITS
     leadership
    0.07
    .createFrom
    0.06
     inclus
    0.06
    208
    0.06
     наÑģÑĤ
    0.06
     mega
    0.06
     dön
    0.06
     Linh
    0.06
    202
    0.06
     stron
    0.06
    Activations Density 0.003%

    No Known Activations