© 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. 29224
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of life and living

    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
    anela
    -0.08
    oca
    -0.07
    วรรà¸ĵ
    -0.07
    Æ°á»Ľng
    -0.07
    illi
    -0.07
    çŃĨ
    -0.06
    xn
    -0.06
    uffer
    -0.06
    orr
    -0.06
    umph
    -0.06
    POSITIVE LOGITS
     bios
    0.06
    opsy
    0.06
     bio
    0.06
    berger
    0.06
     and
    0.06
    disposing
    0.05
     early
    0.05
    early
    0.05
    ayet
    0.05
    emd
    0.05
    Activations Density 0.001%

    No Known Activations