© 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. 84301
    Prev
    Next
    INDEX
    Explanations

    terms related to generalization and standardization

    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
    aper
    -0.07
    anced
    -0.07
    uer
    -0.07
    ment
    -0.07
    ness
    -0.07
    emiz
    -0.06
    åĮĸ
    -0.06
    PointF
    -0.06
    iers
    -0.06
    ç¹
    -0.06
    POSITIVE LOGITS
    eus
    0.07
    orr
    0.07
    obus
    0.07
    ele
    0.07
    dna
    0.06
    ŃIJ
    0.06
    oms
    0.06
    eka
    0.06
    eri
    0.06
    ek
    0.06
    Activations Density 0.023%

    No Known Activations