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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27268
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts relating to query optimization in database management systems

    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
    strup
    -0.07
    @show
    -0.06
    jeta
    -0.06
    inge
    -0.06
    rolling
    -0.06
    ussy
    -0.06
     inh
    -0.06
    ami
    -0.06
     Duffy
    -0.06
    ÑĥеÑĤ
    -0.06
    POSITIVE LOGITS
    atcher
    0.08
     Sawyer
    0.07
    anst
    0.07
    .imag
    0.07
    zas
    0.07
    è¦
    0.06
    XMLLoader
    0.06
    dfa
    0.06
    §
    0.06
    idth
    0.06
    Activations Density 0.010%

    No Known Activations