© 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. 72229
    Prev
    Next
    INDEX
    Explanations

    phrases related to rights and permissions

    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
    unik
    -0.08
    UPPORT
    -0.08
    ycz
    -0.07
    rý
    -0.07
    .Formatter
    -0.07
     hã
    -0.07
    esson
    -0.07
    rys
    -0.07
    æīķ
    -0.07
    až
    -0.07
    POSITIVE LOGITS
     limited
    0.07
     dis
    0.07
     limits
    0.06
    elm
    0.06
    b
    0.06
     any
    0.06
     opport
    0.06
     switches
    0.06
     additional
    0.06
     vary
    0.06
    Activations Density 0.005%

    No Known Activations