© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57868
    Prev
    Next
    INDEX
    Explanations

    references to high significance or notable issues in 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
    ÑĢеб
    -0.08
     nackte
    -0.07
    undo
    -0.07
    /Grid
    -0.07
    elik
    -0.07
    verture
    -0.07
    icros
    -0.07
    ìĬµ
    -0.07
    opens
    -0.06
    opathy
    -0.06
    POSITIVE LOGITS
     being
    0.10
     fact
    0.08
     odds
    0.07
     recent
    0.07
     sometimes
    0.07
     obvious
    0.07
     apparent
    0.07
     Being
    0.07
     having
    0.07
     contrary
    0.07
    Activations Density 0.030%

    No Known Activations