© 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. 74985
    Prev
    Next
    INDEX
    Explanations

    quantifiers that indicate amounts or quantities

    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
    esco
    -0.08
    lech
    -0.06
    ç
    -0.06
    atron
    -0.06
    ingen
    -0.06
    TAIL
    -0.06
    dcc
    -0.06
    ái
    -0.06
    .wp
    -0.06
    ellas
    -0.06
    POSITIVE LOGITS
     since
    0.08
     reasons
    0.08
     purposes
    0.08
     lately
    0.08
     motivo
    0.07
    licted
    0.07
     years
    0.07
    æģ
    0.06
     Since
    0.06
     granted
    0.06
    Activations Density 0.010%

    No Known Activations