© 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. 5005
    Prev
    Next
    INDEX
    Explanations

    actions related to searching and checking for information

    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
     Cousins
    -0.07
    adiens
    -0.07
    елем
    -0.07
    iren
    -0.07
    esting
    -0.06
    outu
    -0.06
    oppel
    -0.06
    ãĢģå°ı
    -0.06
    _ER
    -0.06
    enstein
    -0.06
    POSITIVE LOGITS
     yesterday
    0.07
    ãĥ¼ãĤ¹
    0.07
    éĽĦ
    0.06
     tern
    0.06
     myself
    0.06
    andon
    0.06
    TEM
    0.06
     Composition
    0.06
     Abr
    0.06
    CharCode
    0.06
    Activations Density 0.023%

    No Known Activations