© 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. 81099
    Prev
    Next
    INDEX
    Explanations

    references to text and XML data types

    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
    colo
    -0.07
    êt
    -0.07
    anda
    -0.07
     èŤ
    -0.07
    entence
    -0.06
     NavParams
    -0.06
    DM
    -0.06
    lew
    -0.06
    _globals
    -0.06
    еÑģÑĤÑĮ
    -0.06
    POSITIVE LOGITS
    agos
    0.07
    itt
    0.07
    اعات
    0.07
    endor
    0.06
    opal
    0.06
    ict
    0.06
    IMITER
    0.06
    Ú©ÙĪر
    0.06
    /sign
    0.06
    orthand
    0.06
    Activations Density 0.000%

    No Known Activations