© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95856
    Prev
    Next
    INDEX
    Explanations

    instances of the word "on" used in various contexts

    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
    enate
    -0.07
    moil
    -0.07
    application
    -0.07
     तस
    -0.07
    SWEP
    -0.07
    ียà¸Ķ
    -0.06
    ạc
    -0.06
    ingles
    -0.06
     Orta
    -0.06
    REAK
    -0.06
    POSITIVE LOGITS
     باب
    0.07
    vert
    0.06
    sequ
    0.06
    rid
    0.06
     Rag
    0.06
    QUE
    0.06
     comp
    0.06
    ser
    0.05
    éķľ
    0.05
    vers
    0.05
    Activations Density 0.005%

    No Known Activations