© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78127
    Prev
    Next
    INDEX
    Explanations

    topics related to educational leadership, training, and community engagement

    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
     nihil
    -0.06
    ç¿°
    -0.06
    allon
    -0.06
    виÑĤ
    -0.06
    vester
    -0.06
    asz
    -0.06
    istribution
    -0.06
     Barney
    -0.06
    ẳn
    -0.06
     authDomain
    -0.06
    POSITIVE LOGITS
     basics
    0.09
     leadership
    0.08
    entre
    0.07
     conflict
    0.07
     rud
    0.07
     Conflict
    0.07
     resume
    0.07
     fundamentals
    0.07
     Apprec
    0.06
    leaders
    0.06
    Activations Density 0.048%

    No Known Activations