© 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. 98682
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data manipulation and array handling

    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
    .decorate
    -0.08
    tright
    -0.07
    developer
    -0.07
    ÎŃÏĤ
    -0.07
    ecast
    -0.07
     доÑĤ
    -0.07
    оÑĤов
    -0.07
    voje
    -0.07
    ัมà¸ŀ
    -0.07
    ÑģÑĤÑĢи
    -0.07
    POSITIVE LOGITS
    partials
    0.06
     -
    0.05
    askell
    0.05
    0.05
    acente
    0.05
    ceptive
    0.05
     ones
    0.05
     att
    0.05
     *
    0.05
     Recon
    0.05
    Activations Density 0.022%

    No Known Activations