© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103969
    Prev
    Next
    INDEX
    Explanations

    dates and times in various formats

    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
    zioni
    -0.07
     commercial
    -0.06
    ikut
    -0.06
    bum
    -0.06
     phen
    -0.06
     June
    -0.06
     Gardner
    -0.06
     Commercial
    -0.06
     
    -0.06
     quarters
    -0.05
    POSITIVE LOGITS
     cư
    0.07
    ênh
    0.07
    oppers
    0.07
    ktop
    0.07
    ạnh
    0.07
    ritis
    0.07
    agos
    0.06
     hôm
    0.06
    toy
    0.06
    otive
    0.06
    Activations Density 0.007%

    No Known Activations