© 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. 97399
    Prev
    Next
    INDEX
    Explanations

    mathematical terms related to estimators and limits

    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
    íĭ±
    -0.08
    à¸Ħว
    -0.07
    verity
    -0.07
     réal
    -0.07
    ниÑĨÑĮ
    -0.07
    æ¿Ģ
    -0.06
    Mutable
    -0.06
    (es
    -0.06
    .GridView
    -0.06
    hoot
    -0.06
    POSITIVE LOGITS
    agini
    0.07
    rei
    0.06
     vice
    0.06
    uliar
    0.06
    imuth
    0.06
     detriment
    0.06
     abs
    0.05
    ardown
    0.05
     punct
    0.05
     ens
    0.05
    Activations Density 0.043%

    No Known Activations