© 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. 117602
    Prev
    Next
    INDEX
    Explanations

    references to digital communication technologies or methods

    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
    }elseif
    -0.08
    ornment
    -0.08
     NavParams
    -0.07
    adin
    -0.07
    ĵ
    -0.07
    èĩº
    -0.07
    agal
    -0.07
    dar
    -0.07
    -spinner
    -0.07
    MeasureSpec
    -0.06
    POSITIVE LOGITS
    elle
    0.06
     economy
    0.06
     thrill
    0.06
     crates
    0.06
     Peterson
    0.06
    esa
    0.06
    ÑĢоз
    0.06
    ire
    0.05
     treasure
    0.05
    io
    0.05
    Activations Density 0.039%

    No Known Activations