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. 83003
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes related to stylesheets and viewport settings

    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
     nackte
    -0.07
    άκ
    -0.07
    aleur
    -0.07
     Pres
    -0.07
    Ø·ÙĨ
    -0.06
    alian
    -0.06
     Keystone
    -0.06
    à¤Ŀ
    -0.06
    åĪ·
    -0.06
    ese
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥĭ
    0.07
     Giov
    0.07
    alink
    0.06
     "-//
    0.06
     Scal
    0.06
    rike
    0.06
     Nets
    0.06
    IOR
    0.06
    289
    0.06
    isel
    0.06
    Activations Density 0.003%

    No Known Activations