© 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. 128811
    Prev
    Next
    INDEX
    Explanations

    geographical details related to locations and distances

    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
    sted
    -0.06
    osl
    -0.06
    ÄĽle
    -0.06
    ple
    -0.05
    acy
    -0.05
    Mapped
    -0.05
    _exempt
    -0.05
    inkel
    -0.05
     Dod
    -0.05
    trie
    -0.05
    POSITIVE LOGITS
    erras
    0.07
    Ñģка
    0.07
    	Copyright
    0.07
     дÑĢÑĥго
    0.07
    ÑģÑĸм
    0.06
    ê°IJ
    0.06
    ori
    0.06
    eki
    0.06
     Scalars
    0.06
    رÙħ
    0.06
    Activations Density 0.005%

    No Known Activations