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

    Neuronpedia

    Jacobian LensNEW
    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. 29316
    Prev
    Next
    INDEX
    Explanations

    references to socioeconomic conditions and infrastructure

    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
    ادÙĨ
    -0.07
    adder
    -0.07
    oogle
    -0.07
    ulan
    -0.07
    imli
    -0.07
    oro
    -0.07
    arger
    -0.07
    unch
    -0.07
    ARGER
    -0.06
    -vs
    -0.06
    POSITIVE LOGITS
     ones
    0.32
     Ones
    0.20
    ones
    0.16
     thereof
    0.12
     counterpart
    0.11
    ONES
    0.11
    ãĤĤãģ®
    0.11
     counterparts
    0.10
     others
    0.09
     dit
    0.09
    Activations Density 0.144%

    No Known Activations