© 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. 5075
    Prev
    Next
    INDEX
    Explanations

    technical terms related to algorithms and systems optimization

    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
    orks
    -0.07
    roj
    -0.07
    rocket
    -0.07
    ritel
    -0.07
    dete
    -0.07
    buah
    -0.07
    .scenes
    -0.06
    arat
    -0.06
    scal
    -0.06
    _estimator
    -0.06
    POSITIVE LOGITS
    ูà¸ķ
    0.07
    shima
    0.07
    andin
    0.06
    обÑī
    0.06
    edList
    0.06
     Portions
    0.06
    éĤĬ
    0.06
    WithMany
    0.06
     activities
    0.06
    à¹Ĥล
    0.06
    Activations Density 0.002%

    No Known Activations