© 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. 17-LLAMASCOPE-RES-131K
    11. 130148
    Prev
    Next
    INDEX
    Explanations

    references to rental properties and availability

    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
    amura
    -0.07
    osoph
    -0.07
    olan
    -0.06
    گاÙĨ
    -0.06
    inka
    -0.06
    odon
    -0.06
     Brit
    -0.06
    amber
    -0.06
    ubi
    -0.06
    oub
    -0.06
    POSITIVE LOGITS
     negot
    0.07
     transfer
    0.07
     enqu
    0.07
    æ´
    0.07
    chet
    0.07
     Transfer
    0.07
    transfer
    0.06
    -transfer
    0.06
    emm
    0.06
    539
    0.06
    Activations Density 0.011%

    No Known Activations