© 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 EvalsExportsAPI 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. 126572
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inefficiencies or shortcomings within a system

    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
    idth
    -0.08
    )prepare
    -0.07
    ysize
    -0.07
    uling
    -0.07
    adam
    -0.07
     informations
    -0.07
     mascul
    -0.07
     right
    -0.06
    alo
    -0.06
     got
    -0.06
    POSITIVE LOGITS
    åŀ
    0.07
    inine
    0.07
     karÅŁ
    0.06
    posit
    0.06
    .LookAndFeel
    0.06
    ubyte
    0.06
    ardon
    0.06
    ä¸ī级
    0.06
    rq
    0.06
     asi
    0.06
    Activations Density 0.000%

    No Known Activations