© 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. 55201
    Prev
    Next
    INDEX
    Explanations

    programming constructs and their relationships

    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
    ustos
    -0.07
    à¸Ħรà¸ļ
    -0.06
    zim
    -0.06
     Bout
    -0.06
    vio
    -0.06
    ÙĪÙĩ
    -0.06
    combe
    -0.06
    etched
    -0.06
    hub
    -0.06
     Gh
    -0.05
    POSITIVE LOGITS
     among
    0.13
     find
    0.12
    among
    0.12
     amongst
    0.11
     ÑģÑĢеди
    0.11
     Among
    0.11
     finds
    0.11
    æī¾åĪ°
    0.10
    FindObject
    0.10
    Among
    0.10
    Activations Density 0.101%

    No Known Activations