© 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 EvalsExportsinterp-engineNEWAPI 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. 15171
    Prev
    Next
    INDEX
    Explanations

    terms related to government-imposed restrictions

    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
    ç²
    -0.07
    itled
    -0.06
    ValuePair
    -0.06
     misd
    -0.06
    ilmington
    -0.06
    guarded
    -0.06
    ately
    -0.06
    'field
    -0.06
    /OR
    -0.06
     Clarkson
    -0.06
    POSITIVE LOGITS
    -era
    0.08
     period
    0.08
    æľŁéĹ´
    0.07
    edImage
    0.07
    brero
    0.07
     periods
    0.07
    rez
    0.06
    edin
    0.06
    ovan
    0.06
     era
    0.06
    Activations Density 0.006%

    No Known Activations