© 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. 92672
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and technical notation

    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
    isas
    -0.07
    .experimental
    -0.06
    ãĥ¥
    -0.06
    InstanceOf
    -0.06
    sez
    -0.06
    /owl
    -0.06
    _MODULES
    -0.06
    .trailing
    -0.06
    ovat
    -0.06
     Coff
    -0.06
    POSITIVE LOGITS
    yš
    0.07
    å¼ı
    0.07
    agh
    0.07
    illisecond
    0.07
    anske
    0.06
    STANCE
    0.06
    _simps
    0.06
    ignon
    0.06
    kovi
    0.06
    _checks
    0.06
    Activations Density 0.240%

    No Known Activations