© 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 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. 3538
    Prev
    Next
    INDEX
    Explanations

    terms related to internet domain names and web presence

    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
     forg
    -0.07
    bart
    -0.06
    riger
    -0.06
     lorem
    -0.06
    amer
    -0.06
    uggest
    -0.06
    BITS
    -0.06
    заб
    -0.06
    ius
    -0.06
    etically
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.07
    ÄĽÅĻ
    0.07
    ison
    0.07
    uka
    0.07
    tvrt
    0.07
     sublicense
    0.07
    )prepare
    0.06
     dostate
    0.06
    iphers
    0.06
     daleko
    0.06
    Activations Density 0.000%

    No Known Activations