© 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. 15-LLAMASCOPE-RES-131K
    6. 89086
    Prev
    Next
    INDEX
    Explanations

    references to customer service or assistance

    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
     interrog
    -0.06
    PARSE
    -0.06
    .gstatic
    -0.06
    hta
    -0.06
    Descriptors
    -0.06
    enes
    -0.06
    reater
    -0.06
    sville
    -0.06
    ingu
    -0.06
    iy
    -0.06
    POSITIVE LOGITS
     ÏĦÏģÏĮ
    0.07
    NR
    0.06
    leneck
    0.06
    жд
    0.06
    ato
    0.06
     tread
    0.06
     GRAT
    0.06
    ÅĻez
    0.06
    åĤ
    0.06
    wf
    0.06
    Activations Density 0.000%

    No Known Activations