© 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. 98171
    Prev
    Next
    INDEX
    Explanations

    terms related to cosmology and dark matter density

    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
    .spi
    -0.07
     smo
    -0.06
    CTS
    -0.06
    abay
    -0.06
    _delegate
    -0.06
     Dirty
    -0.06
    away
    -0.06
    ardin
    -0.06
    WO
    -0.06
    ebin
    -0.06
    POSITIVE LOGITS
    .strict
    0.07
    _lite
    0.07
    .poly
    0.06
    leston
    0.06
    Sector
    0.06
    одаÑĢ
    0.06
    å®Ļ
    0.06
    _firestore
    0.06
    ãģĦãģĭ
    0.06
    "in
    0.06
    Activations Density 0.005%

    No Known Activations