© 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. 17-LLAMASCOPE-RES-131K
    11. 76487
    Prev
    Next
    INDEX
    Explanations

    numerical data points related to astronomical or scientific measurements

    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
    isclosed
    -0.07
     wives
    -0.07
    äºŃ
    -0.06
    .sul
    -0.06
     husbands
    -0.06
    lient
    -0.06
    afone
    -0.06
    fy
    -0.06
    ocaly
    -0.06
     Chronic
    -0.06
    POSITIVE LOGITS
     stage
    0.07
    γÎŃν
    0.07
     developmental
    0.07
     formation
    0.07
    AuthToken
    0.07
     Stage
    0.07
     gest
    0.06
    -development
    0.06
     Development
    0.06
     Mat
    0.06
    Activations Density 0.004%

    No Known Activations