© 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. 82837
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rum" and its variations

    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
    cheng
    -0.07
     Bryant
    -0.07
    506
    -0.07
    ằm
    -0.07
    ipa
    -0.07
    istrovstvÃŃ
    -0.06
    onte
    -0.06
    RAP
    -0.06
    اÙĨÙĩ
    -0.06
    à¥Ģय
    -0.06
    POSITIVE LOGITS
    umba
    0.07
    untu
    0.07
    less
    0.07
    dum
    0.07
     rum
    0.06
    ertino
    0.06
    soever
    0.06
    lap
    0.06
    IVEN
    0.06
    ATAR
    0.06
    Activations Density 0.005%

    No Known Activations