Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96164
    Prev
    Next
    INDEX
    Explanations

    terms related to design and inspiration in furniture and decor

    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
     Sesso
    -0.06
     Zem
    -0.06
    pawn
    -0.06
     Blond
    -0.06
     gibi
    -0.06
    rimon
    -0.06
    irty
    -0.06
    icha
    -0.06
    /fast
    -0.06
    izar
    -0.06
    POSITIVE LOGITS
    UED
    0.07
    ToDevice
    0.06
     Stanley
    0.06
    ÅĤu
    0.06
    malink
    0.06
     ï¼¼
    0.06
     Cra
    0.06
    ATUS
    0.06
    ollo
    0.06
     distributions
    0.06
    Activations Density 0.001%

    No Known Activations