© 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. 128780
    Prev
    Next
    INDEX
    Explanations

    instances of the word "nominated" and its variations

    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
    fully
    -0.07
    upt
    -0.07
    rey
    -0.07
    ic
    -0.07
    rea
    -0.07
    ality
    -0.07
    /bit
    -0.06
    ki
    -0.06
    fulness
    -0.06
    -fashioned
    -0.06
    POSITIVE LOGITS
    okane
    0.09
    /lic
    0.07
    atures
    0.07
    astle
    0.07
    ates
    0.07
    ocos
    0.07
    BILE
    0.07
    estic
    0.07
    /******/
    0.07
    estro
    0.06
    Activations Density 0.008%

    No Known Activations