© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15-LLAMASCOPE-RES-131K
    11. 88877
    Prev
    Next
    INDEX
    Explanations

    specific nouns and verbs related to themes of community and shared experiences

    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
    annah
    -0.06
    ĥ
    -0.06
    .intent
    -0.06
     Zwe
    -0.06
    iphone
    -0.06
    usher
    -0.06
     certain
    -0.06
    .yang
    -0.06
    928
    -0.06
    iph
    -0.06
    POSITIVE LOGITS
    ÃŃt
    0.07
    chedulers
    0.06
    åħ¹
    0.06
    亦
    0.06
    биÑĤ
    0.05
    ождениÑı
    0.05
     Chow
    0.05
    ÑĤим
    0.05
     caut
    0.05
    ,copy
    0.05
    Activations Density 0.076%

    No Known Activations