© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 1552
    Prev
    Next
    INDEX
    Explanations

    expressions of desire and intention

    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
    elor
    -0.07
    statt
    -0.07
    ARB
    -0.07
    ungen
    -0.06
    \Modules
    -0.06
    Assertions
    -0.06
    ainment
    -0.06
    ardy
    -0.06
    aux
    -0.06
    uire
    -0.06
    POSITIVE LOGITS
     Hort
    0.07
     Voll
    0.07
    icha
    0.06
    iform
    0.06
    ãĤŃãĥ¥
    0.06
     Schwarz
    0.06
     Willi
    0.06
    QRS
    0.06
    stra
    0.05
     Gül
    0.05
    Activations Density 0.011%

    No Known Activations