© 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. 88435
    Prev
    Next
    INDEX
    Explanations

    geographical locations and company affiliations related to business operations

    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
    InputLabel
    -0.07
    alamat
    -0.07
    reste
    -0.07
    jec
    -0.07
    arkan
    -0.07
    dic
    -0.06
     ÄĮech
    -0.06
    aker
    -0.06
    otten
    -0.06
    боÑĤ
    -0.06
    POSITIVE LOGITS
    ATUS
    0.07
     headquarters
    0.07
     Tucker
    0.07
     company
    0.06
    Chooser
    0.06
     USA
    0.06
    HQ
    0.06
    izard
    0.06
    vester
    0.06
     Scha
    0.06
    Activations Density 0.025%

    No Known Activations