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

    Neuronpedia

    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. 85066
    Prev
    Next
    INDEX
    Explanations

    instances of protests or gatherings, particularly those that are small or in comparison to larger events

    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
    .gov
    -0.07
    AI
    -0.07
    .u
    -0.06
    arro
    -0.06
    stit
    -0.06
    _HINT
    -0.06
     kim
    -0.06
    inki
    -0.06
    ád
    -0.06
    zano
    -0.06
    POSITIVE LOGITS
    ahi
    0.08
    fone
    0.08
    079
    0.07
    locals
    0.07
    raction
    0.07
     Personen
    0.06
    елÑİ
    0.06
    rique
    0.06
    обÑī
    0.06
     вÑĩ
    0.06
    Activations Density 0.000%

    No Known Activations