© 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. 40648
    Prev
    Next
    INDEX
    Explanations

    terms related to copyright and legal protections

    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
    adora
    -0.07
    istrat
    -0.07
    andest
    -0.07
     OPTIONAL
    -0.07
    osity
    -0.07
    postalcode
    -0.07
    аниÑĨ
    -0.07
    İ·
    -0.07
    vore
    -0.07
    enko
    -0.07
    POSITIVE LOGITS
     copyright
    0.08
     Protected
    0.07
     protected
    0.07
     Copyright
    0.07
     Dro
    0.07
     copyrights
    0.07
    iche
    0.07
    OMEM
    0.06
     Emb
    0.06
    acom
    0.06
    Activations Density 0.002%

    No Known Activations