© 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. 15-LLAMASCOPE-RES-131K
    11. 90873
    Prev
    Next
    INDEX
    Explanations

    numerical data and historical references

    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
    etÃŃ
    -0.07
    ullet
    -0.07
    ptic
    -0.07
    etta
    -0.07
    archical
    -0.07
    ModelProperty
    -0.07
    ennes
    -0.07
    epy
    -0.07
    undry
    -0.07
    çľ
    -0.07
    POSITIVE LOGITS
     year
    0.09
     Year
    0.08
     année
    0.08
    year
    0.07
    Year
    0.07
     ann
    0.07
     YEAR
    0.07
    -year
    0.07
     events
    0.07
    année
    0.07
    Activations Density 0.008%

    No Known Activations