© 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. 15-LLAMASCOPE-RES-131K
    6. 26944
    Prev
    Next
    INDEX
    Explanations

    words associated with community engagement and activism

    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
    sters
    -0.08
    ushima
    -0.08
    оваÑĢ
    -0.08
    olet
    -0.08
    erah
    -0.08
    ldb
    -0.07
    ksam
    -0.07
    ething
    -0.07
    term
    -0.07
    zelf
    -0.07
    POSITIVE LOGITS
    ingly
    0.07
    ia
    0.07
    ...">↵
    0.06
    es
    0.06
    aga
    0.06
    azole
    0.06
    ustria
    0.06
    able
    0.06
    909
    0.06
     Instrument
    0.06
    Activations Density 0.092%

    No Known Activations