© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 76640
    Prev
    Next
    INDEX
    Explanations

    concepts related to support structures and training initiatives in organizational change

    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
    /stdc
    -0.08
    ialized
    -0.07
    rita
    -0.07
    ä¹ĭä¸Ģ
    -0.06
    liest
    -0.06
     beled
    -0.06
    ErrorException
    -0.06
    ThreadId
    -0.06
    iol
    -0.06
     ambit
    -0.06
    POSITIVE LOGITS
     etc
    0.08
     depending
    0.07
    usch
    0.06
    .Invariant
    0.06
     gal
    0.06
     bullet
    0.06
    etc
    0.06
     via
    0.06
     purchase
    0.06
    igg
    0.06
    Activations Density 0.042%

    No Known Activations