© 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 EvalsExportsAPI 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. 29335
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical changes and developments

    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
    edom
    -0.07
    ara
    -0.07
    aras
    -0.07
    initial
    -0.06
    isclosed
    -0.06
    Initial
    -0.06
    度
    -0.06
     Initial
    -0.06
     initial
    -0.06
    amac
    -0.06
    POSITIVE LOGITS
     recent
    0.19
     recently
    0.17
    recent
    0.16
     Recent
    0.14
     lately
    0.14
     Recently
    0.13
    Recent
    0.13
     newer
    0.12
    æľĢè¿ij
    0.12
    Recently
    0.12
    Activations Density 0.051%

    No Known Activations