© 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. 17-LLAMASCOPE-RES-131K
    11. 29793
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic survival and fluctuations

    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
     things
    -0.06
    ddy
    -0.06
    iek
    -0.06
    ickle
    -0.06
    äm
    -0.06
     nonzero
    -0.06
    antan
    -0.06
     people
    -0.06
     belg
    -0.05
     Swinger
    -0.05
    POSITIVE LOGITS
    /**↵↵
    0.07
    WEBPACK
    0.07
    axon
    0.07
    _OC
    0.07
    lod
    0.07
    ontology
    0.06
    hev
    0.06
    combe
    0.06
    oa
    0.06
     EMPTY
    0.06
    Activations Density 0.000%

    No Known Activations