© 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. 17-LLAMASCOPE-RES-131K
    11. 117032
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific measurements and research methodologies

    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
    âĹİ
    -0.08
    instanc
    -0.07
    çĿ£
    -0.07
     khá»ıi
    -0.07
    verbosity
    -0.07
    éĺħ读次æķ°
    -0.07
    ศร
    -0.07
    gue
    -0.06
    ̣
    -0.06
    orph
    -0.06
    POSITIVE LOGITS
     studying
    0.08
     measurements
    0.07
     data
    0.07
    eren
    0.07
     gathering
    0.07
    stud
    0.07
     studies
    0.06
    nf
    0.06
     research
    0.06
     scientists
    0.06
    Activations Density 0.015%

    No Known Activations