© 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. 82817
    Prev
    Next
    INDEX
    Explanations

    detailed numerical or statistical data

    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
    yll
    -0.07
    æŁĵ
    -0.07
    ạn
    -0.06
    ÙĪرش
    -0.06
    mins
    -0.06
    weets
    -0.06
    AppState
    -0.06
    ycler
    -0.06
    ostream
    -0.06
     utens
    -0.06
    POSITIVE LOGITS
     population
    0.09
     Census
    0.07
     recorded
    0.07
     popis
    0.07
    population
    0.07
     counted
    0.07
     growth
    0.07
    AGAIN
    0.07
     total
    0.06
     census
    0.06
    Activations Density 0.005%

    No Known Activations