© 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 EvalsExportsinterp-engineNEWAPI 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. 98539
    Prev
    Next
    INDEX
    Explanations

    terms related to heterogeneity in networks and structures

    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
    pear
    -0.08
    endo
    -0.07
    side
    -0.07
    X
    -0.07
    eed
    -0.06
    igo
    -0.06
    /th
    -0.06
    iras
    -0.06
    ÑĥÑģк
    -0.06
    bra
    -0.06
    POSITIVE LOGITS
    itarian
    0.09
    ieties
    0.08
    esses
    0.07
    .fhir
    0.07
    ëŁ
    0.07
     zdrav
    0.07
    uada
    0.07
     имÑĥ
    0.07
    áy
    0.07
    iability
    0.06
    Activations Density 0.013%

    No Known Activations