© 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. 59072
    Prev
    Next
    INDEX
    Explanations

    phrases involving the action of sitting down or coming together for a purpose

    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
    chal
    -0.06
    xt
    -0.06
    led
    -0.06
    alie
    -0.06
    peon
    -0.06
    eldo
    -0.06
    cona
    -0.06
    inç
    -0.06
     ped
    -0.06
    ummings
    -0.05
    POSITIVE LOGITS
    δÏģο
    0.07
     лиÑĨ
    0.07
    roken
    0.07
    _Tis
    0.07
     pornofilm
    0.07
    Ưá»
    0.07
    PageSize
    0.07
     ìķī
    0.07
    spread
    0.06
    ODE
    0.06
    Activations Density 0.003%

    No Known Activations