© 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. 61250
    Prev
    Next
    INDEX
    Explanations

    phrases related to finding and matching personal preferences or needs

    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
    ordion
    -0.07
    ále
    -0.06
    нима
    -0.06
    echan
    -0.06
    æĮģãģ¡
    -0.06
    velop
    -0.06
    áº
    -0.06
     róż
    -0.06
    iske
    -0.06
    ведиÑĤе
    -0.06
    POSITIVE LOGITS
     somewhere
    0.10
     something
    0.08
     match
    0.07
    omething
    0.07
     SOM
    0.07
     найд
    0.07
     find
    0.07
    something
    0.07
     Fitz
    0.07
    =find
    0.07
    Activations Density 0.009%

    No Known Activations