© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95421
    Prev
    Next
    INDEX
    Explanations

    mentions of specific works and releases in popular music and literature

    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
     illustration
    -0.06
    649
    -0.06
    hani
    -0.06
    خت
    -0.06
     Lucas
    -0.06
     pointed
    -0.06
     Illustr
    -0.06
     Luc
    -0.05
     com
    -0.05
     luc
    -0.05
    POSITIVE LOGITS
    ORB
    0.08
    šen
    0.07
    ób
    0.07
    Äįen
    0.07
    éŀ
    0.07
    ahoma
    0.07
    _TypeDef
    0.07
    \grid
    0.07
    BuilderInterface
    0.07
    .RegisterType
    0.07
    Activations Density 0.385%

    No Known Activations