© 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. 105231
    Prev
    Next
    INDEX
    Explanations

    references to academic publications and scientific data

    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
     identity
    -0.07
     loop
    -0.07
    488
    -0.06
    wich
    -0.06
     Loop
    -0.06
    folio
    -0.06
    identity
    -0.05
     borrow
    -0.05
     Brennan
    -0.05
     Ferr
    -0.05
    POSITIVE LOGITS
     centr
    0.08
    uraa
    0.07
     gratuites
    0.07
     Disorder
    0.07
    _ctxt
    0.07
     rencont
    0.07
    HIP
    0.07
     Zombies
    0.07
    tsy
    0.07
    wert
    0.07
    Activations Density 0.094%

    No Known Activations