© 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. 70990
    Prev
    Next
    INDEX
    Explanations

    phrases related to healthcare programs and loan assistance

    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
    lund
    -0.09
     багаÑĤÑĮ
    -0.08
    ãģªãģ©ãģ®
    -0.08
     багаÑĤÑĮоÑħ
    -0.08
    ãģ«åĩº
    -0.08
     gibi
    -0.07
    akis
    -0.07
     etc
    -0.07
    ellas
    -0.07
    cratch
    -0.07
    POSITIVE LOGITS
    /or
    0.09
    /OR
    0.07
     second
    0.07
    second
    0.07
    /from
    0.06
     another
    0.06
     counterpart
    0.06
     followed
    0.06
    another
    0.06
     surtout
    0.06
    Activations Density 0.049%

    No Known Activations