© 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. 9-LLAMASCOPE-RES-131K
    11. 95880
    Prev
    Next
    INDEX
    Explanations

    references to engineering and machinery related to crushers

    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
    igli
    -0.07
    ichtig
    -0.07
    oog
    -0.07
    ardu
    -0.07
    alama
    -0.07
     Hüs
    -0.07
    usch
    -0.06
    urga
    -0.06
     erotik
    -0.06
    raki
    -0.06
    POSITIVE LOGITS
     rico
    0.07
    679
    0.06
    tin
    0.06
    eb
    0.06
    _recovery
    0.06
     ire
    0.06
    ActionCreators
    0.06
     dashes
    0.05
    ative
    0.05
    YPE
    0.05
    Activations Density 0.023%

    No Known Activations