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

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95225
    Prev
    Next
    INDEX
    Explanations

    references to federal funding programs related to broadband access

    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
    rah
    -0.08
    æ¡£
    -0.07
    vat
    -0.07
    etas
    -0.07
    ile
    -0.06
     Toro
    -0.06
    idth
    -0.06
    İĺìĿ´
    -0.06
    757
    -0.06
     NOM
    -0.06
    POSITIVE LOGITS
    dden
    0.07
    abr
    0.07
    udd
    0.07
    udder
    0.06
    uite
    0.06
    pus
    0.06
    Mate
    0.06
    .usage
    0.06
     è¦
    0.06
    Ag
    0.06
    Activations Density 0.001%

    No Known Activations