© 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. 5-LLAMASCOPE-RES-131K
    11. 126969
    Prev
    Next
    INDEX
    Explanations

    terms related to purchasing drugs online, particularly emphasizing affordability

    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
     perhaps
    -0.06
    asher
    -0.06
     all
    -0.06
    dea
    -0.06
    ipp
    -0.06
     only
    -0.06
    cheid
    -0.06
     Shore
    -0.06
    алиÑģÑĤ
    -0.05
    xed
    -0.05
    POSITIVE LOGITS
    ronic
    0.08
    irtual
    0.07
    enance
    0.07
    uche
    0.06
    emode
    0.06
    ÂŃing
    0.06
    orld
    0.06
     Carlton
    0.06
    essen
    0.06
    _ATOMIC
    0.06
    Activations Density 0.003%

    No Known Activations