© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74571
    Prev
    Next
    INDEX
    Explanations

    details related to specific locations and events

    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
    daq
    -0.07
    ãĥ¼ãĥ¬
    -0.06
    adia
    -0.06
    üst
    -0.06
    chin
    -0.06
     Mc
    -0.06
     spect
    -0.06
     Abram
    -0.06
     guest
    -0.05
    ÑĤÑİ
    -0.05
    POSITIVE LOGITS
     delivering
    0.09
     deliveries
    0.08
     Distribution
    0.07
     unloaded
    0.07
    _IE
    0.07
    deliver
    0.07
     Assignment
    0.07
     delivery
    0.07
     Delivery
    0.07
     ServiceException
    0.07
    Activations Density 0.015%

    No Known Activations