© 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. 30807
    Prev
    Next
    INDEX
    Explanations

    references to community events and collective actions

    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
     Barnett
    -0.06
    æŀľ
    -0.06
    PLIC
    -0.06
     regular
    -0.06
     Rivera
    -0.06
    agoon
    -0.06
    _charset
    -0.06
    ETA
    -0.05
     TORT
    -0.05
    election
    -0.05
    POSITIVE LOGITS
     worldwide
    0.09
     participation
    0.09
    åħ¨çIJĥ
    0.08
     Worldwide
    0.08
     simult
    0.08
     Participation
    0.08
     global
    0.08
    global
    0.08
     اÙĦعاÙĦÙħ
    0.07
     Particip
    0.07
    Activations Density 0.017%

    No Known Activations