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

    Neuronpedia

    Jacobian LensNEW
    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. 106711
    Prev
    Next
    INDEX
    Explanations

    the presence of vertical bar characters or similar symbols

    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
    rael
    -0.08
    foy
    -0.07
    lings
    -0.07
    ople
    -0.07
    @brief
    -0.07
    вок
    -0.07
    .googlecode
    -0.07
    주ìĭľ
    -0.07
    opper
    -0.07
    emu
    -0.06
    POSITIVE LOGITS
    ÃĸL
    0.07
     ↵
    0.06
    -feedback
    0.06
     ï¼¼
    0.06
     hä
    0.06
    ãĥ¼ãĥ«
    0.06
    marshall
    0.05
    кав
    0.05
    _exceptions
    0.05
    quis
    0.05
    Activations Density 0.001%

    No Known Activations