© 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. 126120
    Prev
    Next
    INDEX
    Explanations

    numerical values related to real estate and construction measurements

    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
    uos
    -0.07
    nodoc
    -0.07
    891
    -0.07
    ngör
    -0.07
    mentor
    -0.07
    aign
    -0.06
    allis
    -0.06
    mie
    -0.06
    dock
    -0.06
    aran
    -0.06
    POSITIVE LOGITS
    atsby
    0.07
    -sized
    0.07
    -size
    0.06
     sized
    0.06
    ContentSize
    0.06
    pta
    0.06
    ibs
    0.06
    रत
    0.06
     sober
    0.06
    Chance
    0.06
    Activations Density 0.016%

    No Known Activations