© 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. 15-LLAMASCOPE-RES-131K
    11. 87396
    Prev
    Next
    INDEX
    Explanations

    mentions of social media platforms or tagging symbols

    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
    echan
    -0.08
    apesh
    -0.07
    utsch
    -0.07
    DataTask
    -0.07
    apel
    -0.07
    ĥ
    -0.07
    porno
    -0.07
    ntax
    -0.07
    ÄĽn
    -0.07
     Kemp
    -0.07
    POSITIVE LOGITS
    792
    0.06
    owitz
    0.06
     like
    0.05
    let
    0.05
     the
    0.05
     sav
    0.05
    787
    0.05
     cub
    0.05
     cl
    0.05
    оÑĢоÑĪ
    0.05
    Activations Density 0.000%

    No Known Activations