© 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. 84267
    Prev
    Next
    INDEX
    Explanations

    phrases related to authorship and ownership

    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
    ãĤĵãģ©
    -0.07
    thane
    -0.07
    лÑİ
    -0.07
     Burns
    -0.06
    ãģ£ãģ¨
    -0.06
    isel
    -0.06
    ãģŃ
    -0.06
    annon
    -0.06
     lam
    -0.06
    ndl
    -0.06
    POSITIVE LOGITS
     cannot
    0.08
     neither
    0.08
     not
    0.08
     nowhere
    0.07
     nothing
    0.07
    cannot
    0.06
     nobody
    0.06
    ä¸įèĥ½
    0.06
    ogle
    0.06
     NOT
    0.06
    Activations Density 0.007%

    No Known Activations