© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95087
    Prev
    Next
    INDEX
    Explanations

    geographical locations and landmarks

    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
    esty
    -0.08
    414
    -0.07
    actories
    -0.07
    IVA
    -0.07
    FullPath
    -0.07
    ivas
    -0.06
    upply
    -0.06
     поÑĢÑıд
    -0.06
    aky
    -0.06
    ulace
    -0.06
    POSITIVE LOGITS
    utin
    0.07
    ufs
    0.06
    alo
    0.06
    infer
    0.06
     uncon
    0.06
     Yates
    0.06
    asto
    0.06
     Trainer
    0.06
    uga
    0.06
    echa
    0.06
    Activations Density 0.015%

    No Known Activations