© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28595
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal disclaimers and liability

    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
    ows
    -0.07
    yon
    -0.06
    &W
    -0.06
    ippo
    -0.06
    ewise
    -0.06
    aldi
    -0.06
    alu
    -0.06
    isia
    -0.06
    èĭ
    -0.06
    createClass
    -0.06
    POSITIVE LOGITS
    ndl
    0.07
    ñana
    0.07
    _DIRECT
    0.07
    å±ĭ
    0.06
    RAND
    0.06
    lle
    0.06
    Ing
    0.06
     tesis
    0.06
    buz
    0.06
    ÑģоÑĤ
    0.06
    Activations Density 0.001%

    No Known Activations