© 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. 28274
    Prev
    Next
    INDEX
    Explanations

    terms related to queries and data binding in a technical or database context

    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
     ABC
    -0.08
    abus
    -0.07
    æĮ¯ãĤĬ
    -0.07
    ABC
    -0.07
     abc
    -0.07
    PLICIT
    -0.07
     useClass
    -0.06
     Tune
    -0.06
    'Ñı
    -0.06
    ãģ¤ãģ¶
    -0.06
    POSITIVE LOGITS
     HOR
    0.07
    adius
    0.07
    iox
    0.06
     Elim
    0.06
     fier
    0.06
    วà¸ĩ
    0.06
     clauses
    0.06
    claimer
    0.06
    _INST
    0.06
     Hemp
    0.06
    Activations Density 0.020%

    No Known Activations