© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71067
    Prev
    Next
    INDEX
    Explanations

    references to loneliness

    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
    _ACL
    -0.07
    еÑĢж
    -0.06
    babel
    -0.06
    eo
    -0.06
    bull
    -0.06
    mond
    -0.06
    ACS
    -0.06
    oid
    -0.06
    د
    -0.06
    ea
    -0.06
    POSITIVE LOGITS
    eliness
    0.09
    ely
    0.08
    orch
    0.08
    ewolf
    0.07
    elong
    0.07
    esome
    0.07
    eness
    0.07
    ELY
    0.07
     Fork
    0.07
    ework
    0.07
    Activations Density 0.015%

    No Known Activations