© 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. 75091
    Prev
    Next
    INDEX
    Explanations

    terms related to individuals being unaccounted for or absent

    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
    ¦æĥħ
    -0.07
    meric
    -0.07
    èn
    -0.07
    alia
    -0.07
    ollider
    -0.07
    essel
    -0.07
    bers
    -0.07
    ä»ĺãģij
    -0.07
    usto
    -0.07
    loth
    -0.06
    POSITIVE LOGITS
    lust
    0.06
    pending
    0.06
    enschaft
    0.06
     eventually
    0.06
     trace
    0.06
     presumed
    0.06
     pending
    0.05
     whereabouts
    0.05
     coinc
    0.05
     Herb
    0.05
    Activations Density 0.006%

    No Known Activations