© 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. 31042
    Prev
    Next
    INDEX
    Explanations

    instances of sharing or email-related 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
    gether
    -0.06
    áš
    -0.06
    ego
    -0.06
    336
    -0.06
    engkap
    -0.06
    ashtra
    -0.06
     MEN
    -0.06
    488
    -0.06
    atti
    -0.05
    796
    -0.05
    POSITIVE LOGITS
    roje
    0.07
     jadx
    0.07
    neider
    0.07
     meiden
    0.06
    //---------------------------------------------------------------------------↵↵
    0.06
    nant
    0.06
     propor
    0.06
     плен
    0.06
    groupid
    0.06
    ÑģеÑĢ
    0.06
    Activations Density 0.002%

    No Known Activations