© 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. 9-LLAMASCOPE-RES-131K
    11. 98010
    Prev
    Next
    INDEX
    Explanations

    inquiries related to costs and measurements in various 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
     transfer
    -0.06
    izr
    -0.06
     weather
    -0.06
    sson
    -0.06
    IGIN
    -0.06
    PLIT
    -0.06
     unless
    -0.06
    _weather
    -0.06
    703
    -0.06
    erval
    -0.05
    POSITIVE LOGITS
    umas
    0.07
    opher
    0.07
    .protobuf
    0.07
     McCart
    0.07
    ubre
    0.07
     åIJĦ
    0.06
    icol
    0.06
    ä½
    0.06
    vim
    0.06
     telefone
    0.06
    Activations Density 0.033%

    No Known Activations