© 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 EvalsExportsinterp-engineNEWAPI 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. 70343
    Prev
    Next
    INDEX
    Explanations

    expressions of desire and requests for something or anything

    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
     Nor
    -0.07
    omu
    -0.07
     nor
    -0.07
     Brad
    -0.07
    ntag
    -0.06
     cose
    -0.06
    Ñģли
    -0.06
    Nor
    -0.06
    aco
    -0.06
    kola
    -0.06
    POSITIVE LOGITS
     ANY
    0.21
     any
    0.19
    -any
    0.18
     anything
    0.18
    ANY
    0.17
     anywhere
    0.17
    anything
    0.17
    any
    0.16
     Anything
    0.16
    ä»»ä½ķ
    0.16
    Activations Density 0.035%

    No Known Activations