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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16548
    Prev
    Next
    INDEX
    Explanations

    terms related to government benefits and financial support systems for older adults

    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
     ro
    -0.07
     seat
    -0.06
     Seat
    -0.06
     Dad
    -0.06
     str
    -0.06
     eth
    -0.06
     char
    -0.05
     Daddy
    -0.05
     ting
    -0.05
    acula
    -0.05
    POSITIVE LOGITS
    WithMany
    0.08
    /basic
    0.08
     hö
    0.08
    ÑĸнÑĮ
    0.07
    tesy
    0.07
    amus
    0.07
    _allocated
    0.07
    krom
    0.07
    subcategory
    0.07
    licos
    0.07
    Activations Density 0.022%

    No Known Activations