© 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. 60979
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers or data points

    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
    _UNUSED
    -0.07
    untu
    -0.07
    olin
    -0.07
     unb
    -0.07
    akat
    -0.07
     unut
    -0.07
    .Txt
    -0.07
    acf
    -0.06
    опÑĢи
    -0.06
    374
    -0.06
    POSITIVE LOGITS
     Orc
    0.06
    -toggler
    0.06
    //*[@
    0.06
    undry
    0.06
    :"",
    0.06
     Partnership
    0.06
    ëıħ
    0.06
     Headquarters
    0.06
    νε
    0.06
    oga
    0.06
    Activations Density 0.002%

    No Known Activations