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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 26971
    Prev
    Next
    INDEX
    Explanations

    specific identifiers related to hotel facilities and services

    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
    serrat
    -0.08
    >:</
    -0.07
    azon
    -0.07
    ]={↵
    -0.07
    -fit
    -0.07
    chio
    -0.07
    ën
    -0.07
    аÑĩе
    -0.07
    .AddListener
    -0.07
    ocache
    -0.07
    POSITIVE LOGITS
    yer
    0.07
    iator
    0.06
    yers
    0.06
    //
    0.06
    ï¸ı
    0.06
    Ī
    0.05
    owi
    0.05
    its
    0.05
    ibs
    0.05
     martyr
    0.05
    Activations Density 0.023%

    No Known Activations