© 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. 104932
    Prev
    Next
    INDEX
    Explanations

    relationships involving influence or impact 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
    gın
    -0.07
    éĽij
    -0.07
     toto
    -0.07
     ikt
    -0.07
    toi
    -0.07
    adm
    -0.06
     зави
    -0.06
     enim
    -0.06
    orman
    -0.06
    ีà¹ī
    -0.06
    POSITIVE LOGITS
     wherever
    0.11
     whichever
    0.07
     its
    0.07
    whatever
    0.07
     whoever
    0.07
    ãĥģ
    0.07
     whenever
    0.07
     whatever
    0.06
    ils
    0.06
     Whoever
    0.06
    Activations Density 0.082%

    No Known Activations