© 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. 84308
    Prev
    Next
    INDEX
    Explanations

    references to technical implementation and integration details in software development

    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
    âłĢ
    -0.07
     ISSN
    -0.07
    berg
    -0.07
    elu
    -0.06
    SError
    -0.06
    reh
    -0.06
     Compiled
    -0.06
    quet
    -0.06
    apro
    -0.06
     âŁ
    -0.06
    POSITIVE LOGITS
    .yahoo
    0.07
    yahoo
    0.07
    _parms
    0.07
     enhancement
    0.07
     Enhancement
    0.06
    aterno
    0.06
    @yahoo
    0.06
    ãĤĴãģĬ
    0.06
    alamat
    0.06
    ìĿ´ë²Ħ
    0.06
    Activations Density 0.026%

    No Known Activations