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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 104172
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases that depict a sense of nostalgia or history

    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
    ãģĵãģ¨ãģ¯
    -0.07
     Tube
    -0.07
    ków
    -0.06
    жд
    -0.06
    oba
    -0.06
     Sink
    -0.06
    remen
    -0.06
    Mine
    -0.06
     Module
    -0.06
    _fold
    -0.06
    POSITIVE LOGITS
    usercontent
    0.09
     somehow
    0.08
    uffer
    0.07
    ntax
    0.07
    endor
    0.07
    UpInside
    0.06
    INAL
    0.06
     rather
    0.06
     somewhere
    0.06
     overnight
    0.06
    Activations Density 0.015%

    No Known Activations