© 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. 59434
    Prev
    Next
    INDEX
    Explanations

    terms referring to reliability or dependability

    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
    Ñģед
    -0.07
    adol
    -0.07
     kab
    -0.07
    ibal
    -0.07
     Helsinki
    -0.07
     Herb
    -0.07
     каб
    -0.07
     Kab
    -0.06
    zyst
    -0.06
    lisi
    -0.06
    POSITIVE LOGITS
    oplay
    0.06
     dig
    0.06
     discret
    0.06
     vind
    0.06
    orts
    0.06
    ifo
    0.06
    POR
    0.06
     hire
    0.06
     æĪ
    0.06
    dust
    0.06
    Activations Density 0.000%

    No Known Activations