© 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. 5-LLAMASCOPE-RES-131K
    11. 126100
    Prev
    Next
    INDEX
    Explanations

    terms related to travel logistics and processes

    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
    ties
    -0.07
    htub
    -0.06
     Cabinets
    -0.06
    TEL
    -0.06
    elor
    -0.06
     stamp
    -0.06
    tu
    -0.06
     Laboratories
    -0.06
    enta
    -0.06
    oped
    -0.06
    POSITIVE LOGITS
    olle
    0.08
    LEAR
    0.07
    ÅĻez
    0.07
    cej
    0.07
    umlu
    0.06
    äre
    0.06
    utin
    0.06
    indle
    0.06
    Mock
    0.06
    zdy
    0.06
    Activations Density 0.156%

    No Known Activations