© 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. 1895
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions taken to ensure safety and compliance

    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
    veau
    -0.06
    RULE
    -0.06
    939
    -0.06
    .sy
    -0.06
    amt
    -0.06
    Iss
    -0.06
    LEM
    -0.06
    оÑģÑĮ
    -0.06
     Iss
    -0.06
    lom
    -0.06
    POSITIVE LOGITS
    ibase
    0.07
    оÑĢоз
    0.07
     reasonably
    0.07
    ãĤ¤ãĤº
    0.07
    iras
    0.06
    ensus
    0.06
    _TYPEDEF
    0.06
    rog
    0.06
    illet
    0.06
    uchen
    0.06
    Activations Density 0.001%

    No Known Activations