© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 106564
    Prev
    Next
    INDEX
    Explanations

    topics related to authority and societal challenges

    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
    roys
    -0.08
    .SetToolTip
    -0.07
    oy
    -0.07
    atel
    -0.07
    antis
    -0.07
    egend
    -0.07
    olicit
    -0.07
    ково
    -0.07
    ilda
    -0.07
    ilde
    -0.07
    POSITIVE LOGITS
     increasingly
    0.10
    åį´
    0.08
     becomes
    0.08
     become
    0.08
     wonder
    0.08
    åį»
    0.07
     Wonder
    0.07
    focus
    0.07
     wondered
    0.06
     increasing
    0.06
    Activations Density 0.061%

    No Known Activations