© 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. 57373
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to art, culture, and community events

    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
    Âł
    -0.07
    alsa
    -0.06
    zung
    -0.06
    óst
    -0.06
    sembles
    -0.06
     instead
    -0.05
     flush
    -0.05
     string
    -0.05
    ábado
    -0.05
    alled
    -0.05
    POSITIVE LOGITS
    &display
    0.07
    /Peak
    0.07
     ragaz
    0.07
    olleyError
    0.07
     alike
    0.07
     WARRANT
    0.07
    ZF
    0.07
    #
    0.07
    utorial
    0.07
    ovalo
    0.07
    Activations Density 0.062%

    No Known Activations