© 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. 120084
    Prev
    Next
    INDEX
    Explanations

    designations or labels associated with application and patent information

    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
    etto
    -0.06
     Amer
    -0.06
    okit
    -0.06
     Passage
    -0.06
    "),"
    -0.06
     SPI
    -0.06
    629
    -0.06
    ãĥ¼ãĥIJ
    -0.06
    Ú¯ÛĮر
    -0.06
    AMP
    -0.06
    POSITIVE LOGITS
    urret
    0.07
    ween
    0.07
    avad
    0.07
    kish
    0.06
    rido
    0.06
    udas
    0.06
    ¤
    0.06
    utton
    0.06
    stances
    0.06
    udit
    0.06
    Activations Density 0.001%

    No Known Activations