© 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. 73015
    Prev
    Next
    INDEX
    Explanations

    contractions related to possession or desire

    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
    ’Ñıз
    -0.08
    luv
    -0.07
    ardy
    -0.07
    zell
    -0.07
    eah
    -0.07
    amt
    -0.07
    urdu
    -0.07
    idon
    -0.07
    âĻª
    -0.07
    idl
    -0.07
    POSITIVE LOGITS
    ham
    0.06
    iag
    0.06
    Specifier
    0.06
    ाà¤Ĺ
    0.06
    =wx
    0.06
    aja
    0.06
     behalf
    0.06
     sake
    0.05
    (es
    0.05
    ä»Ģä¹Ī
    0.05
    Activations Density 0.020%

    No Known Activations