© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26867
    Prev
    Next
    INDEX
    Explanations

    references to access and control of sensitive or confidential information

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    onga
    -0.08
    ãĥ¼ãĥ©
    -0.08
    zÃŃ
    -0.08
     sơ
    -0.07
    rego
    -0.07
     porad
    -0.07
    erea
    -0.07
    ameleon
    -0.07
    zee
    -0.07
    avou
    -0.07
    POSITIVE LOGITS
     ret
    0.07
     relevant
    0.06
     access
    0.06
     employees
    0.06
    rog
    0.06
    AccessType
    0.05
     Access
    0.05
     personnel
    0.05
    hip
    0.05
    esin
    0.05
    Activations Density 0.001%

    No Known Activations