© 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. 2044
    Prev
    Next
    INDEX
    Explanations

    phrases related to systems or processes referencing structure and functioning

    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
    illions
    -0.08
     многиÑħ
    -0.07
     thousands
    -0.07
    ÑĥÑĢÑģ
    -0.07
     Thousands
    -0.07
     many
    -0.07
     doubly
    -0.07
     Twice
    -0.07
    Thousands
    -0.07
     BOTH
    -0.07
    POSITIVE LOGITS
     each
    0.12
     EACH
    0.11
    each
    0.11
    åĪĨåĪ«
    0.10
     nhau
    0.09
    _each
    0.09
     Each
    0.09
     cada
    0.09
    (each
    0.09
     ê°ģê°ģ
    0.09
    Activations Density 0.081%

    No Known Activations