© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76657
    Prev
    Next
    INDEX
    Explanations

    discussions about social and political movements advocating for change

    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
    ppard
    -0.08
    uhn
    -0.07
    ughs
    -0.07
    ansa
    -0.07
    rais
    -0.07
    otron
    -0.06
    огÑĢаÑĦ
    -0.06
     Landing
    -0.06
    apsed
    -0.06
    UGH
    -0.06
    POSITIVE LOGITS
     unstoppable
    0.07
     slowly
    0.07
     momentum
    0.07
     increasingly
    0.07
     tidal
    0.06
    _already
    0.06
     already
    0.06
    anium
    0.06
     movement
    0.06
    .mass
    0.06
    Activations Density 0.038%

    No Known Activations