© 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 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. 9-LLAMASCOPE-RES-131K
    11. 96537
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to neutron stars and their properties

    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
     Burl
    -0.08
    εί
    -0.07
     ziy
    -0.07
    rame
    -0.07
     Honest
    -0.07
    ACA
    -0.06
    jte
    -0.06
    ollectors
    -0.06
    eyen
    -0.06
    ples
    -0.06
    POSITIVE LOGITS
    osate
    0.07
    _firestore
    0.07
    oard
    0.07
    iability
    0.06
    Jun
    0.06
    ulo
    0.06
    znik
    0.06
    оÑĢод
    0.05
     state
    0.05
    iable
    0.05
    Activations Density 0.011%

    No Known Activations