© 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. 93920
    Prev
    Next
    INDEX
    Explanations

    mentions of software services and applications related to 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
    yas
    -0.09
    .datab
    -0.08
    _Tis
    -0.08
    даÑı
    -0.08
    odos
    -0.08
    rink
    -0.07
    letal
    -0.07
    RuntimeObject
    -0.07
    ige
    -0.07
    igen
    -0.07
    POSITIVE LOGITS
    eder
    0.08
     ones
    0.06
     Pearl
    0.06
    baum
    0.06
     Grass
    0.06
    VERTISE
    0.06
     Vall
    0.06
    ↵
    0.06
    ë¶Ģ
    0.06
    RIA
    0.06
    Activations Density 0.011%

    No Known Activations