© 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. 95020
    Prev
    Next
    INDEX
    Explanations

    phrases that express varying degrees of assessment or evaluation

    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
    oret
    -0.08
    ØŃ
    -0.07
    ctl
    -0.07
     Grat
    -0.07
    را
    -0.06
     èµ
    -0.06
    duk
    -0.06
    _OC
    -0.06
     Gle
    -0.06
    ëĭĺìĿ´
    -0.06
    POSITIVE LOGITS
    awner
    0.07
    oard
    0.06
    ductory
    0.06
    ä¹ĭä¸Ģ
    0.06
    ifact
    0.06
    attery
    0.06
    quer
    0.06
    reme
    0.06
    atement
    0.06
    ocker
    0.06
    Activations Density 0.002%

    No Known Activations