© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 125479
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and terms related to physics or theoretical models

    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
    nze
    -0.07
    NEY
    -0.07
    lds
    -0.07
     Kurd
    -0.07
    licit
    -0.06
    миниÑģÑĤÑĢа
    -0.06
    urtles
    -0.06
    agna
    -0.06
    .weixin
    -0.06
    TTY
    -0.06
    POSITIVE LOGITS
    _reordered
    0.06
     JACK
    0.06
     Hor
    0.06
    uu
    0.06
    igma
    0.06
    icons
    0.05
    (void
    0.05
    ulin
    0.05
    oundingBox
    0.05
    152
    0.05
    Activations Density 0.005%

    No Known Activations