© 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. 61646
    Prev
    Next
    INDEX
    Explanations

    references to locations and actions related to heights and elevations

    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
    HEMA
    -0.07
    erset
    -0.07
    unga
    -0.07
    LEAN
    -0.07
    declar
    -0.07
    ¦Ĥ
    -0.07
    ulis
    -0.07
    cale
    -0.07
    uib
    -0.07
    alla
    -0.06
    POSITIVE LOGITS
     below
    0.18
     Below
    0.16
    ä¸ĭ
    0.15
    below
    0.15
    Below
    0.15
     ä¸ĭ
    0.14
     вниз
    0.14
     BELOW
    0.13
    _below
    0.12
     bottom
    0.12
    Activations Density 0.072%

    No Known Activations