© 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. 30028
    Prev
    Next
    INDEX
    Explanations

    references to restrictions on social gatherings

    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
    ãĤ·ãĥ£ãĥ«
    -0.07
    raci
    -0.06
    ollar
    -0.06
    anganese
    -0.06
    irit
    -0.06
    cth
    -0.06
     pun
    -0.06
    TURE
    -0.06
    _parm
    -0.06
    вок
    -0.06
    POSITIVE LOGITS
    adera
    0.08
     capacity
    0.07
    capacity
    0.07
     persons
    0.07
     capacities
    0.07
     Capacity
    0.06
     seated
    0.06
     sle
    0.06
     gratuites
    0.06
     mÃŃt
    0.06
    Activations Density 0.002%

    No Known Activations