© 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. 9-LLAMASCOPE-RES-131K
    11. 98765
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to mathematical models and frameworks

    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
    Å¡ek
    -0.07
    age
    -0.07
    hani
    -0.07
    æłª
    -0.07
     margin
    -0.07
    istrovstvÃŃ
    -0.07
    heit
    -0.07
    lates
    -0.07
    ance
    -0.06
    vál
    -0.06
    POSITIVE LOGITS
    ertz
    0.09
    ematic
    0.07
    ieu
    0.07
    зв
    0.07
    atical
    0.07
    reopen
    0.07
    iterr
    0.07
    uro
    0.07
    ematik
    0.06
    owie
    0.06
    Activations Density 0.016%

    No Known Activations