© 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. 27740
    Prev
    Next
    INDEX
    Explanations

    phrases related to data management and information disclosure

    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
    lbrace
    -0.07
    /Gate
    -0.06
    lum
    -0.06
    jak
    -0.06
    iku
    -0.06
     gall
    -0.06
    lates
    -0.06
    /framework
    -0.06
    ObjectName
    -0.06
    aal
    -0.06
    POSITIVE LOGITS
     fields
    0.10
     information
    0.10
    _fields
    0.10
    fields
    0.09
     Fields
    0.09
    FIELDS
    0.09
    /stdc
    0.08
    -information
    0.08
    Fields
    0.08
    -fields
    0.08
    Activations Density 0.033%

    No Known Activations