© 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. 82135
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of physical spaces and their elements

    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
    chw
    -0.06
    adr
    -0.06
    ghi
    -0.06
    vo
    -0.06
    mdir
    -0.06
    ÙħÛĮÙĨ
    -0.06
    owe
    -0.05
     Tower
    -0.05
     Vocal
    -0.05
     tower
    -0.05
    POSITIVE LOGITS
     room
    0.17
    room
    0.14
    æĪ¿éĹ´
    0.14
     Room
    0.14
    Room
    0.13
    ROOM
    0.13
    -room
    0.13
     ROOM
    0.13
    _room
    0.12
     roomId
    0.11
    Activations Density 0.086%

    No Known Activations