© 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. 16540
    Prev
    Next
    INDEX
    Explanations

    expressions of support and advocacy for health and social policies

    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
    ternet
    -0.07
    SORT
    -0.07
     UNU
    -0.07
    oom
    -0.07
    anmar
    -0.07
    ely
    -0.07
    abo
    -0.06
    _TOPIC
    -0.06
    _TRACE
    -0.06
     Antar
    -0.06
    POSITIVE LOGITS
     demands
    0.07
     demand
    0.06
    rong
    0.06
     hopes
    0.06
    ront
    0.06
     demande
    0.06
     hope
    0.06
    æķ¦
    0.06
     HO
    0.06
    269
    0.05
    Activations Density 0.020%

    No Known Activations