© 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. 9-LLAMASCOPE-RES-131K
    11. 95684
    Prev
    Next
    INDEX
    Explanations

    phrases related to tourism and travel activities

    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
    ESC
    -0.07
     str
    -0.06
    bac
    -0.06
    CAA
    -0.06
     Junk
    -0.06
     Expedition
    -0.06
    Mixin
    -0.06
    AGED
    -0.06
    ulia
    -0.06
    erif
    -0.05
    POSITIVE LOGITS
     Avery
    0.07
    ìĹŃ
    0.06
    orem
    0.06
     longer
    0.06
     nghiá»ĩp
    0.06
     pione
    0.06
    ève
    0.06
    GLE
    0.06
    _Selection
    0.06
    gae
    0.06
    Activations Density 0.001%

    No Known Activations