© 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. 55483
    Prev
    Next
    INDEX
    Explanations

    phrases indicating increases and decreases in variables or quantities within a scientific context

    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
    iber
    -0.07
     migrationBuilder
    -0.07
     à¤ľà¤Ĺ
    -0.07
    /theme
    -0.07
    /browse
    -0.07
     meiden
    -0.07
    formace
    -0.07
    nonnull
    -0.07
     nackte
    -0.07
    -0.07
    POSITIVE LOGITS
    $MESS
    0.07
    oug
    0.07
    uhn
    0.06
    seealso
    0.06
    oodle
    0.06
    protect
    0.06
    icari
    0.06
    isto
    0.06
    imei
    0.06
    ĴĮ
    0.06
    Activations Density 0.172%

    No Known Activations