© 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. 41351
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of standing up or taking a stand

    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
    osit
    -0.07
    osc
    -0.07
    osate
    -0.07
    lc
    -0.07
    uling
    -0.06
    itals
    -0.06
    le
    -0.06
    osite
    -0.06
     нада
    -0.06
    itus
    -0.06
    POSITIVE LOGITS
    -alone
    0.08
    _stand
    0.07
     stands
    0.07
    igm
    0.07
     stood
    0.07
     stand
    0.07
     amen
    0.07
     united
    0.07
     padd
    0.06
    µ¬
    0.06
    Activations Density 0.011%

    No Known Activations