Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61094
    Prev
    Next
    INDEX
    Explanations

    technical terms related to measurement and sensor technology

    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
    /the
    -0.10
    the
    -0.09
     the
    -0.08
    â̦the
    -0.08
    ,the
    -0.08
    (the
    -0.08
    The
    -0.07
    theid
    -0.07
    	the
    -0.07
     The
    -0.07
    POSITIVE LOGITS
    anine
    0.08
    .si
    0.08
    веÑī
    0.08
     personel
    0.07
    ÅĻejmÄĽ
    0.07
     POSSIBILITY
    0.07
    ityEngine
    0.07
    idar
    0.07
    enderit
    0.07
     moden
    0.07
    Activations Density 0.051%

    No Known Activations