© 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. 76868
    Prev
    Next
    INDEX
    Explanations

    academic and professional terms related to education, health, and literacy

    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
    лага
    -0.07
    abase
    -0.07
    istrovstvÃŃ
    -0.07
    sink
    -0.07
    sitemap
    -0.07
    asje
    -0.07
    sert
    -0.06
    imens
    -0.06
     Shib
    -0.06
    imiter
    -0.06
    POSITIVE LOGITS
     Daw
    0.06
     cr
    0.06
    osoph
    0.06
    dept
    0.06
    'gc
    0.06
     cap
    0.06
     gul
    0.06
    otionEvent
    0.05
     department
    0.05
    _topology
    0.05
    Activations Density 0.053%

    No Known Activations