© 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. 62073
    Prev
    Next
    INDEX
    Explanations

    occurrences of parameter annotations in code comments

    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
    isoft
    -0.07
    isen
    -0.06
    PLUGIN
    -0.06
     STDCALL
    -0.06
    lena
    -0.06
    ittance
    -0.06
    .Q
    -0.06
    ystate
    -0.06
    iov
    -0.06
    елиÑĩ
    -0.06
    POSITIVE LOGITS
     string
    0.07
     bool
    0.07
     {*}
    0.06
    ÑĪиб
    0.06
    매
    0.06
     int
    0.06
     groupBox
    0.06
    ìĭ¤
    0.06
    ropolitan
    0.06
    tü
    0.06
    Activations Density 0.004%

    No Known Activations