© 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. 9-LLAMASCOPE-RES-131K
    11. 97517
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or terms of service related to liability and disclaimers

    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
    eras
    -0.07
    inoa
    -0.07
    egg
    -0.06
    ammen
    -0.06
    tec
    -0.06
    rial
    -0.06
    nee
    -0.06
    urse
    -0.06
    nar
    -0.06
    pron
    -0.06
    POSITIVE LOGITS
    .EventType
    0.07
    اÙĦÙĦÙĩ
    0.06
    Serialized
    0.06
     æľ¨
    0.06
    CHAIN
    0.06
    _TS
    0.06
    à¥ĩस
    0.06
    Ascii
    0.06
    macen
    0.06
    ASCII
    0.06
    Activations Density 0.017%

    No Known Activations