© 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. 61419
    Prev
    Next
    INDEX
    Explanations

    phrases related to numerical values and measurements

    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
    strup
    -0.07
     è«
    -0.06
    arat
    -0.06
    outines
    -0.06
    ALLOC
    -0.06
     slopes
    -0.06
    XE
    -0.06
    fec
    -0.06
    ala
    -0.06
    IfNeeded
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.07
    .googlecode
    0.07
    435
    0.07
    oren
    0.07
     handic
    0.07
    ymous
    0.07
    bilt
    0.06
    935
    0.06
    455
    0.06
    UNK
    0.06
    Activations Density 0.003%

    No Known Activations