© 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. 17-LLAMASCOPE-RES-131K
    11. 56812
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the word "As" in various contexts

    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
    tas
    -0.08
    ovation
    -0.07
    zeug
    -0.07
    ondo
    -0.07
    activ
    -0.07
    ously
    -0.07
    hare
    -0.07
    actively
    -0.07
    isce
    -0.07
    Orm
    -0.07
    POSITIVE LOGITS
    paragus
    0.09
    sembl
    0.09
    coli
    0.09
    pects
    0.08
     melhores
    0.08
     far
    0.07
    gard
    0.07
    riel
    0.07
    utral
    0.07
    imes
    0.07
    Activations Density 0.034%

    No Known Activations