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. 87578
    Prev
    Next
    INDEX
    Explanations

    instances of emotional connection and caregiving

    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
    çŃĭ
    -0.07
    chw
    -0.06
    лоб
    -0.06
    ibling
    -0.06
    Ãły
    -0.06
    emetery
    -0.06
    inea
    -0.06
    ãĤĤãģªãģĦ
    -0.06
     currently
    -0.06
    Sibling
    -0.06
    POSITIVE LOGITS
     última
    0.08
     late
    0.07
    bove
    0.07
     posled
    0.07
     whenever
    0.07
     last
    0.06
     último
    0.06
     últ
    0.06
     últimos
    0.06
    ToMany
    0.06
    Activations Density 0.022%

    No Known Activations