© 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. 103619
    Prev
    Next
    INDEX
    Explanations

    phrases related to travel logistics and flexibility

    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
    æ
    -0.08
    ombine
    -0.08
    ittings
    -0.08
    ulfill
    -0.08
    hea
    -0.08
    èĭĹ
    -0.08
    weetalert
    -0.08
    ANNEL
    -0.08
    iap
    -0.07
     nues
    -0.07
    POSITIVE LOGITS
    eras
    0.07
    erras
    0.06
     fabric
    0.06
    5
    0.06
     gamb
    0.06
     local
    0.06
     pace
    0.05
     Local
    0.05
    2
    0.05
     sym
    0.05
    Activations Density 0.004%

    No Known Activations