© 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. 5115
    Prev
    Next
    INDEX
    Explanations

    phrases related to reviews and evaluations of media

    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
    amine
    -0.07
    ãĥ©ãĤ¹
    -0.06
    elu
    -0.06
    amin
    -0.06
     watt
    -0.06
    ektir
    -0.06
     bar
    -0.06
    CurrentValue
    -0.06
    emark
    -0.05
    entifier
    -0.05
    POSITIVE LOGITS
     mostly
    0.07
     Clover
    0.07
    rava
    0.07
    ones
    0.07
    .IContainer
    0.06
    Та
    0.06
     Mostly
    0.06
    SetBranch
    0.06
    ãģŁãģ¡
    0.06
    оÑħ
    0.06
    Activations Density 0.004%

    No Known Activations