© 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. 71968
    Prev
    Next
    INDEX
    Explanations

    phrases related to community engagement and support initiatives

    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
    <decltype
    -0.08
     Seymour
    -0.07
    究
    -0.07
     basically
    -0.07
    ãĥªãĥ³ãĤ°
    -0.07
     åħ¶
    -0.07
    ãģ©
    -0.07
    اÛĮÙĨ
    -0.07
    Ïĥμο
    -0.07
    _CT
    -0.06
    POSITIVE LOGITS
     several
    0.07
    raith
    0.06
    aut
    0.06
     Several
    0.06
     Starting
    0.06
    cano
    0.06
    .CreateIndex
    0.06
     Profession
    0.06
    Several
    0.06
    individual
    0.06
    Activations Density 0.030%

    No Known Activations