© 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. 108159
    Prev
    Next
    INDEX
    Explanations

    references to organization and structure within texts

    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
    zos
    -0.07
    uliar
    -0.07
    ("(%
    -0.07
    gue
    -0.06
    aks
    -0.06
    cord
    -0.06
    oleon
    -0.06
    olis
    -0.06
    essim
    -0.06
     undercut
    -0.06
    POSITIVE LOGITS
     external
    0.27
     outside
    0.23
    external
    0.23
    å¤ĸ
    0.23
     External
    0.22
    External
    0.21
     extern
    0.21
    _external
    0.20
     exterior
    0.20
     outer
    0.19
    Activations Density 0.044%

    No Known Activations