Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71289
    Prev
    Next
    INDEX
    Explanations

    details related to startup programs and accelerators

    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
    rod
    -0.06
    ERP
    -0.06
     discret
    -0.06
    opr
    -0.06
    Animating
    -0.06
    auen
    -0.06
    ocker
    -0.06
    krom
    -0.06
    fixtures
    -0.06
    ayers
    -0.06
    POSITIVE LOGITS
     incub
    0.10
     accelerator
    0.10
     Pitch
    0.09
     pitch
    0.09
     angel
    0.08
     acceler
    0.08
    Pitch
    0.08
     pitching
    0.08
     Startup
    0.08
     Plug
    0.08
    Activations Density 0.118%

    No Known Activations