© 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. 69429
    Prev
    Next
    INDEX
    Explanations

    function and method calls related to data retrieval and manipulation

    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
     perse
    -0.07
    ovah
    -0.07
    alfa
    -0.07
    uo
    -0.07
    aaaaaaaa
    -0.07
    ilik
    -0.06
    zte
    -0.06
    ä¹Ĺ
    -0.06
    DDS
    -0.06
    usk
    -0.06
    POSITIVE LOGITS
    OrDefault
    0.07
    exion
    0.07
    à¹ģล
    0.06
    (()
    0.06
    mas
    0.06
     Civ
    0.06
    ocks
    0.05
     "[%
    0.05
    нем
    0.05
    XP
    0.05
    Activations Density 0.021%

    No Known Activations