© 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. 17-LLAMASCOPE-RES-131K
    11. 128617
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future actions or roles

    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
    abcdefghijkl
    -0.07
    ansi
    -0.06
    оÑĢаÑı
    -0.06
    cpt
    -0.06
    olland
    -0.06
     tonight
    -0.06
    addon
    -0.06
     Welch
    -0.06
    pb
    -0.06
    splash
    -0.06
    POSITIVE LOGITS
    cest
    0.07
    éĺ´
    0.06
     Compensation
    0.06
     Barrett
    0.06
     compensation
    0.06
    tep
    0.06
    ewan
    0.06
     preferably
    0.06
    isson
    0.06
     Moder
    0.06
    Activations Density 0.005%

    No Known Activations