© 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. 128072
    Prev
    Next
    INDEX
    Explanations

    details about hotel features and offerings

    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
    Ïħγ
    -0.08
    onders
    -0.07
    enson
    -0.07
    tainment
    -0.07
    -tm
    -0.07
    esini
    -0.07
    ãĤ¢ãĥ³
    -0.07
    taire
    -0.07
    vetica
    -0.07
    Inline
    -0.07
    POSITIVE LOGITS
     breakfast
    0.08
     Breakfast
    0.07
     Transparency
    0.07
     transparency
    0.06
     beds
    0.06
    629
    0.06
     Wellness
    0.06
     elevator
    0.05
     wellness
    0.05
     street
    0.05
    Activations Density 0.004%

    No Known Activations