© 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. 78398
    Prev
    Next
    INDEX
    Explanations

    specific terms related to reports and documentation

    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
     bis
    -0.06
    orthand
    -0.06
     ras
    -0.06
    ¶Į
    -0.05
     "..
    -0.05
    Ñģол
    -0.05
    евиÑĩ
    -0.05
     ведÑĮ
    -0.05
    .annot
    -0.05
    POSITIVE LOGITS
    bilt
    0.07
    uced
    0.07
    __);
    0.07
    rema
    0.07
    obb
    0.06
     is
    0.06
    asser
    0.06
    assin
    0.06
     are
    0.06
     à¤ĩत
    0.06
    Activations Density 0.053%

    No Known Activations