© 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. 105959
    Prev
    Next
    INDEX
    Explanations

    terms related to abundance and quantity

    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
    ëł´
    -0.07
    ãĥ§
    -0.07
    TOTYPE
    -0.07
    виÑĩай
    -0.06
     backpage
    -0.06
    .SelectedItems
    -0.06
    /Instruction
    -0.06
    ï¼
    -0.06
    UTE
    -0.06
    ===↵
    -0.06
    POSITIVE LOGITS
     throughout
    0.09
    olare
    0.08
     among
    0.07
    ÑĢÑĥд
    0.07
     everywhere
    0.06
     but
    0.06
    ä¸Ķ
    0.06
    dden
    0.06
    GD
    0.06
    itals
    0.06
    Activations Density 0.016%

    No Known Activations