© 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 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. 3603
    Prev
    Next
    INDEX
    Explanations

    phrases indicating positivity and enthusiasm about a subject or project

    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
     itself
    -0.10
    elper
    -0.07
    iras
    -0.06
    izia
    -0.06
    angan
    -0.06
    own
    -0.06
    erspective
    -0.06
    $MESS
    -0.06
    xies
    -0.06
    imized
    -0.06
    POSITIVE LOGITS
     anon
    0.07
    .EntityManager
    0.06
    дин
    0.06
     humanity
    0.06
    gil
    0.06
     Slov
    0.06
    maz
    0.06
    ivel
    0.06
     sorry
    0.06
    StateException
    0.06
    Activations Density 0.013%

    No Known Activations