© 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. 126629
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating authorship or agency

    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
    031
    -0.07
    inalg
    -0.07
    throp
    -0.06
    undler
    -0.06
    à¹Ģà¸Ńà¸ĩ
    -0.06
     fur
    -0.06
    -kit
    -0.06
    ycler
    -0.06
     Greg
    -0.05
    ogan
    -0.05
    POSITIVE LOGITS
    eyen
    0.07
    ordes
    0.07
     ÄIJo
    0.07
    ailles
    0.06
    antium
    0.06
    akk
    0.06
    ahl
    0.06
    ignon
    0.06
    elin
    0.06
     millions
    0.06
    Activations Density 0.001%

    No Known Activations