© 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. 79324
    Prev
    Next
    INDEX
    Explanations

    concerns related to safety in electrical work

    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
     tone
    -0.06
    avana
    -0.06
     Kir
    -0.05
    éĻ£
    -0.05
     implic
    -0.05
     ton
    -0.05
    ifes
    -0.05
     beats
    -0.05
     Camel
    -0.05
    :↵
    -0.05
    POSITIVE LOGITS
    dorf
    0.08
    áºŃt
    0.08
    quential
    0.07
     vyk
    0.07
    MethodManager
    0.07
    гÑĢа
    0.07
    mere
    0.07
    á»ķ
    0.07
     kodu
    0.07
    IEW
    0.07
    Activations Density 0.002%

    No Known Activations