© 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. 71820
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize necessity and requirements

    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
     addCriterion
    -0.09
    maktan
    -0.08
    ITHER
    -0.08
    lamÄ±ÅŁ
    -0.07
    ibu
    -0.07
    CLUD
    -0.07
    одо
    -0.07
    /dom
    -0.07
    _ib
    -0.07
    xad
    -0.07
    POSITIVE LOGITS
     needed
    0.09
    needed
    0.08
     necessary
    0.07
     sufficient
    0.07
     Needed
    0.06
     need
    0.06
     ticket
    0.06
    Needed
    0.06
    onn
    0.06
     needs
    0.06
    Activations Density 0.005%

    No Known Activations