© 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. 29143
    Prev
    Next
    INDEX
    Explanations

    terms associated with data analysis and synchronization

    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
     vs
    -0.07
    arro
    -0.07
     Vs
    -0.07
     versus
    -0.07
    vs
    -0.06
    -vs
    -0.06
    è£ı
    -0.06
    .Localization
    -0.06
    eming
    -0.06
    fur
    -0.06
    POSITIVE LOGITS
     between
    0.22
    between
    0.19
     Between
    0.19
     междÑĥ
    0.18
    Between
    0.17
    _between
    0.17
     BETWEEN
    0.17
     zwischen
    0.16
    -between
    0.16
     мÑĸж
    0.16
    Activations Density 0.094%

    No Known Activations