© 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. 17-LLAMASCOPE-RES-131K
    11. 75522
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of" 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
    oom
    -0.07
    oss
    -0.07
    ä¸Ģ人
    -0.07
    eos
    -0.06
    _UNS
    -0.06
    overs
    -0.06
    èĶµ
    -0.06
    оÑĢоз
    -0.06
    çıł
    -0.06
    оÑĢÑĸв
    -0.06
    POSITIVE LOGITS
    andler
    0.08
    venes
    0.07
    uen
    0.07
    owell
    0.07
    ibel
    0.07
    reira
    0.07
    reta
    0.06
    onis
    0.06
    odef
    0.06
    ogan
    0.06
    Activations Density 0.009%

    No Known Activations