© 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. 9-LLAMASCOPE-RES-131K
    11. 98179
    Prev
    Next
    INDEX
    Explanations

    mentions of people and their names

    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
    odem
    -0.08
    -wow
    -0.08
    ryn
    -0.07
    entin
    -0.07
    chia
    -0.07
    lij
    -0.07
    ape
    -0.07
    ardy
    -0.07
    ót
    -0.07
    ovi
    -0.07
    POSITIVE LOGITS
     Acquisition
    0.06
    rogen
    0.06
    .opensource
    0.06
    579
    0.06
    ?=
    0.06
     âĢ¦↵
    0.06
    dk
    0.06
    âĢ¦↵↵↵
    0.06
     Lal
    0.06
     acquisition
    0.06
    Activations Density 0.024%

    No Known Activations