© 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. 75208
    Prev
    Next
    INDEX
    Explanations

    features related to construction or structural elements

    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
    ály
    -0.08
    nze
    -0.08
    MemoryWarning
    -0.07
     amen
    -0.06
    duino
    -0.06
    onym
    -0.06
    ylinder
    -0.06
    .scalablytyped
    -0.06
    lane
    -0.06
    coli
    -0.06
    POSITIVE LOGITS
     installation
    0.07
     wall
    0.07
     install
    0.07
     Installation
    0.07
     Hang
    0.07
    -install
    0.06
    .wall
    0.06
     screws
    0.06
     Flush
    0.06
    installation
    0.06
    Activations Density 0.003%

    No Known Activations