© 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. 118820
    Prev
    Next
    INDEX
    Explanations

    discussions around expectations and obligations in various contexts

    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
    idy
    -0.07
     cov
    -0.07
    quent
    -0.06
    rors
    -0.06
    elp
    -0.06
    dur
    -0.06
    indy
    -0.06
    rv
    -0.06
    .GraphicsUnit
    -0.06
     NR
    -0.06
    POSITIVE LOGITS
     shouldn
    0.10
     ought
    0.10
    should
    0.10
     should
    0.10
     SHOULD
    0.10
    Should
    0.09
    _should
    0.09
     Should
    0.09
    ought
    0.08
     deber
    0.08
    Activations Density 0.062%

    No Known Activations