© 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. 108223
    Prev
    Next
    INDEX
    Explanations

    indicators of trust and reliability in relationships and experiences

    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
     ÅĽw
    -0.07
    _GRP
    -0.07
    029
    -0.07
    alist
    -0.07
    ilos
    -0.06
    141
    -0.06
    lio
    -0.06
    .memo
    -0.06
    quina
    -0.06
    ÑģÑİ
    -0.06
    POSITIVE LOGITS
    trust
    0.07
     trust
    0.07
     recip
    0.07
     undert
    0.07
     trustworthy
    0.06
     trusted
    0.06
     undertake
    0.06
     trusts
    0.06
    PF
    0.06
    abric
    0.06
    Activations Density 0.013%

    No Known Activations