© 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. 22-LLAMASCOPE-RES-131K
    11. 4327
    Prev
    Next
    INDEX
    Explanations

    features and amenities related to hotel accommodations

    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
    ÅĻi
    -0.08
    eyim
    -0.08
    .nano
    -0.08
    ayız
    -0.07
    PIO
    -0.07
    lesai
    -0.07
    話
    -0.07
    codegen
    -0.07
    iedo
    -0.07
    vider
    -0.07
    POSITIVE LOGITS
     Prim
    0.07
     ting
    0.06
    lining
    0.06
     poles
    0.06
    âĢIJ
    0.06
     pup
    0.06
    ound
    0.06
     freely
    0.06
    rak
    0.05
     property
    0.05
    Activations Density 0.002%

    No Known Activations