© 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. 79982
    Prev
    Next
    INDEX
    Explanations

    words expressing hope or optimism

    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
    ĪæĿĥ
    -0.07
    inan
    -0.06
    å·
    -0.06
    iden
    -0.06
    rant
    -0.06
    ãģ®ãģłãĤįãģĨ
    -0.06
    anguage
    -0.06
    anst
    -0.06
    ensively
    -0.06
    adelphia
    -0.06
    POSITIVE LOGITS
    585
    0.08
     there
    0.07
     ÙĩÙĨاÙĥ
    0.07
    abler
    0.07
    illac
    0.07
    there
    0.07
    IONS
    0.06
    engin
    0.06
    zes
    0.06
     عÙĦÙĬÙĥ
    0.06
    Activations Density 0.010%

    No Known Activations