© 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. 16607
    Prev
    Next
    INDEX
    Explanations

    elements related to academic requirements and guidelines

    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
    ellow
    -0.07
    VML
    -0.07
    нав
    -0.07
    irth
    -0.07
     schooling
    -0.07
    hoa
    -0.07
     schools
    -0.07
    erti
    -0.07
    lsru
    -0.07
    ¥IJ
    -0.06
    POSITIVE LOGITS
    .assignment
    0.07
    inas
    0.07
     Canvas
    0.07
     class
    0.07
    structor
    0.06
     lecture
    0.06
     MIME
    0.06
    chalk
    0.06
    rame
    0.06
     course
    0.06
    Activations Density 0.053%

    No Known Activations