© 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. 42286
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology and concepts related to object manipulation and representation

    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
     Emerson
    -0.06
    BuilderFactory
    -0.06
    aina
    -0.06
    ém
    -0.06
    acro
    -0.06
    bond
    -0.06
     Miss
    -0.06
     Fram
    -0.06
    wit
    -0.06
    atters
    -0.06
    POSITIVE LOGITS
     lá»iji
    0.07
    _COMPAT
    0.07
     dere
    0.07
    298
    0.06
     Berm
    0.06
     operator
    0.06
    446
    0.06
    -operator
    0.06
     Winn
    0.06
     Rencontre
    0.06
    Activations Density 0.011%

    No Known Activations