© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 83473
    Prev
    Next
    INDEX
    Explanations

    numeric values and associated identifiers within structured data

    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
    ÙĬÙĦاد
    -0.07
    erif
    -0.07
    krom
    -0.07
    784
    -0.06
     )}↵↵
    -0.06
    imm
    -0.06
    기ê´Ģ
    -0.06
    /tutorial
    -0.06
    ãĥ¼ãĥ©
    -0.06
    eru
    -0.06
    POSITIVE LOGITS
    /LICENSE
    0.07
     ->
    0.06
     Robbins
    0.06
    stadt
    0.06
     Clyde
    0.05
     Prompt
    0.05
    ARRIER
    0.05
     and
    0.05
     Tara
    0.05
    ectar
    0.05
    Activations Density 0.063%

    No Known Activations