© 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. 108388
    Prev
    Next
    INDEX
    Explanations

    mentions of "new" in various contexts

    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
    alat
    -0.07
    .nb
    -0.07
    CallCheck
    -0.07
    OLON
    -0.06
    ÙĦÙĤ
    -0.06
     Term
    -0.06
     Stamp
    -0.06
     lon
    -0.06
    orgen
    -0.06
    à¹ģ
    -0.06
    POSITIVE LOGITS
    yr
    0.08
    omed
    0.07
    wor
    0.07
    adora
    0.06
     Copies
    0.06
     mandate
    0.06
    mand
    0.06
    oÄį
    0.06
    andra
    0.06
    PED
    0.06
    Activations Density 0.000%

    No Known Activations