© 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. 104744
    Prev
    Next
    INDEX
    Explanations

    phrases related to threats and risks

    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
    sher
    -0.07
    ilton
    -0.07
    otions
    -0.06
    oci
    -0.06
    isp
    -0.06
    ech
    -0.06
    rey
    -0.06
    urga
    -0.06
    ä¹
    -0.06
    ói
    -0.06
    POSITIVE LOGITS
    HeaderCode
    0.10
    theid
    0.07
    ingly
    0.07
    GuidId
    0.07
    ANI
    0.07
    NewProp
    0.07
    ereo
    0.07
    MBER
    0.07
    QT
    0.07
    690
    0.06
    Activations Density 0.006%

    No Known Activations