© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 136
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic resistance and cancer mechanisms

    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
    REFER
    -0.09
    sizei
    -0.08
    ROUT
    -0.07
    AdapterManager
    -0.07
     pestic
    -0.07
    PCODE
    -0.07
    ddy
    -0.07
    ://${
    -0.07
    odata
    -0.07
    мÑĭ
    -0.07
    POSITIVE LOGITS
     Rob
    0.06
     mod
    0.06
     targets
    0.06
     m
    0.06
     regulation
    0.06
     fractions
    0.06
     undis
    0.06
     promise
    0.06
     how
    0.06
     cons
    0.06
    Activations Density 0.063%

    No Known Activations