© 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. 70395
    Prev
    Next
    INDEX
    Explanations

    phrases related to errors and issues in processes

    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
    isd
    -0.06
    uck
    -0.06
    acing
    -0.06
    av
    -0.06
     sca
    -0.06
    alon
    -0.06
    owie
    -0.06
     viol
    -0.06
    ÑģÑĤанов
    -0.06
    oud
    -0.06
    POSITIVE LOGITS
    egt
    0.07
    mux
    0.07
    poons
    0.07
    rung
    0.06
    rif
    0.06
     somewhere
    0.06
    .unknown
    0.06
    PLL
    0.06
    виÑī
    0.06
    ÏĨη
    0.06
    Activations Density 0.003%

    No Known Activations