© 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. 29748
    Prev
    Next
    INDEX
    Explanations

    elements related to support systems and initiatives in educational or organizational 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
    ull
    -0.07
    uir
    -0.07
     generations
    -0.06
     sole
    -0.06
    UI
    -0.06
    stice
    -0.06
     Sole
    -0.06
    erea
    -0.06
    pak
    -0.06
    onds
    -0.06
    POSITIVE LOGITS
     regional
    0.16
    åIJĦ
    0.16
     individual
    0.15
     each
    0.15
    each
    0.14
     åIJĦ
    0.14
     Regional
    0.14
     Each
    0.14
    individual
    0.14
     ê°ģ
    0.13
    Activations Density 0.173%

    No Known Activations