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. 78557
    Prev
    Next
    INDEX
    Explanations

    themes of disillusionment with government and social issues

    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
    FileVersion
    -0.08
    ekim
    -0.07
    prak
    -0.07
    ebi
    -0.07
    ibox
    -0.07
    TimeInterval
    -0.07
    cola
    -0.07
    amba
    -0.07
    eci
    -0.07
    /Typography
    -0.07
    POSITIVE LOGITS
     institutions
    0.07
     conventional
    0.07
     existing
    0.06
     traditional
    0.06
    ailed
    0.06
     politicians
    0.06
     feeling
    0.06
     failures
    0.06
     mainstream
    0.06
     hopeless
    0.06
    Activations Density 0.036%

    No Known Activations