© 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. 62397
    Prev
    Next
    INDEX
    Explanations

    terms related to network ports and their configurations

    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
    pagesize
    -0.07
    ìłĿ
    -0.06
    å¨ľ
    -0.06
    ãĥ¼ãĥĬ
    -0.06
    ury
    -0.06
     parch
    -0.06
     Stark
    -0.06
    bilt
    -0.06
     proport
    -0.06
    hend
    -0.05
    POSITIVE LOGITS
     port
    0.08
    åı·
    0.07
    çķªåı·
    0.07
    port
    0.07
    listen
    0.07
    fec
    0.07
    èĻŁ
    0.07
    ãĥ¼ãĥ¬
    0.07
    range
    0.07
    -port
    0.07
    Activations Density 0.013%

    No Known Activations