© 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. 1709
    Prev
    Next
    INDEX
    Explanations

    proper nouns and words related to academia and research

    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
    gravity
    -0.07
     gravity
    -0.07
    brig
    -0.07
    emens
    -0.06
    iw
    -0.06
    ména
    -0.06
    /unit
    -0.06
    sterol
    -0.06
    isters
    -0.06
     stren
    -0.06
    POSITIVE LOGITS
    lifetime
    0.07
    Ķ
    0.07
    .Serializer
    0.06
     lifetime
    0.06
     Düz
    0.06
    TestData
    0.06
    -ÑĤаки
    0.06
    umpt
    0.06
    uger
    0.06
    OfWork
    0.06
    Activations Density 0.058%

    No Known Activations