© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75405
    Prev
    Next
    INDEX
    Explanations

    references to anatomical structures and their evolutionary implications

    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
    Lifecycle
    -0.06
    ixa
    -0.06
     atmos
    -0.06
     way
    -0.06
     deb
    -0.06
     Bek
    -0.06
    wich
    -0.06
     delivery
    -0.06
    owitz
    -0.06
     Advisory
    -0.06
    POSITIVE LOGITS
     developmental
    0.09
     morph
    0.08
    morph
    0.08
    ecom
    0.08
    thon
    0.07
     коÑģÑĤ
    0.07
     Morph
    0.07
    arth
    0.07
    characters
    0.07
    aina
    0.07
    Activations Density 0.019%

    No Known Activations