Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29255
    Prev
    Next
    INDEX
    Explanations

    terms related to online marketing techniques

    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
    _ALIGNMENT
    -0.07
    cratch
    -0.07
     Redistributions
    -0.07
    лоÑĩ
    -0.07
     mastur
    -0.07
    _locator
    -0.07
    quier
    -0.07
    .CreateInstance
    -0.07
    èµı
    -0.07
     hâl
    -0.07
    POSITIVE LOGITS
     interest
    0.06
     based
    0.06
     re
    0.06
     excluded
    0.06
     abandoned
    0.06
     tact
    0.06
     omn
    0.06
     immedi
    0.06
     prospect
    0.05
     stalk
    0.05
    Activations Density 0.003%

    No Known Activations