© 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. 88696
    Prev
    Next
    INDEX
    Explanations

    geographical locations and administrative regions

    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
     Pierce
    -0.07
    .builders
    -0.06
    edriver
    -0.06
    iaux
    -0.06
    eyer
    -0.06
    reh
    -0.06
    raci
    -0.06
    abbo
    -0.06
    adoo
    -0.06
     tetas
    -0.06
    POSITIVE LOGITS
    gorithm
    0.07
     pÅĤ
    0.06
    tü
    0.06
     branch
    0.06
    -to
    0.06
    æ³¥
    0.06
    ignKey
    0.06
    ìļ©
    0.06
    ICAST
    0.06
    ó
    0.06
    Activations Density 0.019%

    No Known Activations