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. 16461
    Prev
    Next
    INDEX
    Explanations

    positive feedback and gratitude related to wedding performances

    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
     Olymp
    -0.07
    elta
    -0.07
    ãĥį
    -0.06
     nob
    -0.06
    antry
    -0.06
    Watcher
    -0.06
    ajas
    -0.06
    çŃĨ
    -0.06
    aktu
    -0.06
    _this
    -0.06
    POSITIVE LOGITS
     Hire
    0.08
     hire
    0.08
     Bride
    0.07
    elop
    0.07
     hired
    0.07
     Hiring
    0.07
    batim
    0.07
     wedding
    0.07
     hires
    0.07
    /npm
    0.07
    Activations Density 0.016%

    No Known Activations