© 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. 61855
    Prev
    Next
    INDEX
    Explanations

    phrases related to cost and expenses in various contexts

    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
    /or
    -0.10
    /of
    -0.06
    ikan
    -0.06
    ÑĢÑĸз
    -0.06
    ete
    -0.05
    wel
    -0.05
     etc
    -0.05
    .s
    -0.05
    @dynamic
    -0.05
     Rudd
    -0.05
    POSITIVE LOGITS
    ignet
    0.08
    cene
    0.08
    rame
    0.08
    erdem
    0.07
    ãĥ¼ãĥĦ
    0.07
    .onView
    0.07
    elp
    0.07
    tura
    0.07
    sic
    0.07
    abyrinth
    0.07
    Activations Density 0.030%

    No Known Activations