© 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 EvalsExportsinterp-engineNEWAPI 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. 117464
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and indicators of complexity in scientific and analytical contexts

    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
    {})
    -0.06
    adiens
    -0.06
    нож
    -0.06
    ius
    -0.05
    ourg
    -0.05
    ÃŃg
    -0.05
    wig
    -0.05
    ÇIJ
    -0.05
    å¯
    -0.05
     trp
    -0.05
    POSITIVE LOGITS
     see
    0.16
    see
    0.15
     details
    0.14
     See
    0.14
    See
    0.13
    详
    0.13
     http
    0.13
     https
    0.12
    details
    0.12
    详æĥħ
    0.11
    Activations Density 0.087%

    No Known Activations