© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 124812
    Prev
    Next
    INDEX
    Explanations

    concepts related to leadership and collaboration

    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
     ëĭ´
    -0.07
    .house
    -0.07
    ẩu
    -0.07
    ederland
    -0.06
    xo
    -0.06
    loys
    -0.06
    ejs
    -0.06
    бин
    -0.06
    ecz
    -0.06
    itm
    -0.06
    POSITIVE LOGITS
     leadership
    0.15
     Leadership
    0.14
     leader
    0.13
    leaders
    0.12
    Leaders
    0.12
     Leader
    0.12
    leader
    0.10
    Leader
    0.10
     Followers
    0.10
     leaders
    0.10
    Activations Density 0.018%

    No Known Activations