© 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. 69643
    Prev
    Next
    INDEX
    Explanations

    references to growth and future potential across 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
     etc
    -0.08
    �
    -0.07
    etc
    -0.06
     halt
    -0.06
    c
    -0.06
    ora
    -0.06
     ins
    -0.06
     Hat
    -0.06
    337
    -0.06
    ect
    -0.06
    POSITIVE LOGITS
    LOPT
    0.08
    .Editor
    0.08
    ÑĪки
    0.08
    aset
    0.07
    _exempt
    0.07
    ukkit
    0.07
    .WinForms
    0.07
     Indexed
    0.07
    InBackground
    0.07
    ëĮĢ를
    0.07
    Activations Density 0.025%

    No Known Activations