© 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. 17-LLAMASCOPE-RES-131K
    6. 106997
    Prev
    Next
    INDEX
    Explanations

    technical terms and equations related to physics or engineering

    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
     manic
    -0.07
    late
    -0.06
    ctl
    -0.06
    anic
    -0.06
    پر
    -0.06
    quent
    -0.06
    аÑĤив
    -0.06
     home
    -0.06
    ampo
    -0.06
     late
    -0.06
    POSITIVE LOGITS
    (IDC
    0.08
    ingles
    0.07
    ajas
    0.07
    \web
    0.07
    SmartPointer
    0.07
     Ridley
    0.07
    ìĪĺë¡ľ
    0.06
     Wish
    0.06
    è¡Ŀ
    0.06
    URLConnection
    0.06
    Activations Density 0.054%

    No Known Activations