© 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. 82814
    Prev
    Next
    INDEX
    Explanations

    expressions related to guidance, reference, or support 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
    ationship
    -0.07
    kir
    -0.07
    ué
    -0.07
    rana
    -0.06
    itm
    -0.06
     GRE
    -0.06
    osomal
    -0.06
    ods
    -0.06
    sched
    -0.06
    och
    -0.06
    POSITIVE LOGITS
    ediator
    0.07
     guide
    0.07
    )test
    0.06
     unofficial
    0.06
    erva
    0.06
    hen
    0.06
     Springs
    0.06
    .Named
    0.06
     Smy
    0.06
    lando
    0.06
    Activations Density 0.022%

    No Known Activations