© 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. 87214
    Prev
    Next
    INDEX
    Explanations

    expressions and concepts related to healing

    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
    .TestTools
    -0.09
    ải
    -0.08
    å¸ĸ
    -0.08
    æ¨
    -0.08
    orial
    -0.08
    ted
    -0.07
    ãģŁãĤī
    -0.07
    ality
    -0.07
    curso
    -0.07
    curring
    -0.07
    POSITIVE LOGITS
    úsqueda
    0.08
    overy
    0.07
    inger
    0.06
    /rest
    0.06
     Gaw
    0.06
    828
    0.06
    lest
    0.06
    ijk
    0.06
    (er
    0.06
     process
    0.06
    Activations Density 0.005%

    No Known Activations