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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 93671
    Prev
    Next
    INDEX
    Explanations

    words related to age and generational context

    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
    -0.07
    -0.06
    âĢ³
    -0.06
     “
    -0.06
    ordova
    -0.06
    usk
    -0.06
    OUS
    -0.06
     Arbor
    -0.06
    hire
    -0.05
    âĢ²
    -0.05
    POSITIVE LOGITS
    ataire
    0.08
    ltra
    0.08
    ecko
    0.08
    ’hui
    0.08
     ³³ ³³ ³³ ³³
    0.08
    urname
    0.08
    ÄĽt
    0.08
    legt
    0.08
    -wsj
    0.08
     addCriterion
    0.08
    Activations Density 0.273%

    No Known Activations