© 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. 28818
    Prev
    Next
    INDEX
    Explanations

    percentage values and their significance in a medical or analytical context

    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
    azen
    -0.06
    leg
    -0.06
    ning
    -0.06
     Gay
    -0.06
    quote
    -0.06
     æ®
    -0.06
    igel
    -0.06
    lang
    -0.06
    iface
    -0.06
    eme
    -0.06
    POSITIVE LOGITS
     Podesta
    0.07
    _None
    0.06
    CHANT
    0.06
    .none
    0.06
    erchant
    0.06
    IMS
    0.06
    çi
    0.06
    >:</
    0.06
    «
    0.06
    룡
    0.06
    Activations Density 0.001%

    No Known Activations