© 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. 107536
    Prev
    Next
    INDEX
    Explanations

    terms related to granting permissions or rights

    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
    ãĥ¼ãĤ¹ãĥĪ
    -0.09
    uet
    -0.07
    hai
    -0.07
    sie
    -0.07
    squ
    -0.07
    yük
    -0.07
    .Trace
    -0.07
    isel
    -0.07
     gì
    -0.07
    éļľ
    -0.07
    POSITIVE LOGITS
     permission
    0.12
    permission
    0.08
     permissions
    0.08
     access
    0.08
     Permission
    0.07
     relief
    0.06
     passage
    0.06
    äºĪ
    0.06
    pher
    0.06
    permissions
    0.06
    Activations Density 0.007%

    No Known Activations