© 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. 14967
    Prev
    Next
    INDEX
    Explanations

    key phrases related to film releases and their formats

    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
    ibs
    -0.06
    ODULE
    -0.06
    à¹Ģà¸Ĺà¸ŀ
    -0.06
    igators
    -0.06
    icap
    -0.06
     /**<
    -0.06
     Stall
    -0.06
    令
    -0.06
    adamente
    -0.06
    publish
    -0.06
    POSITIVE LOGITS
    âĢ«
    0.08
    aised
    0.07
     retailers
    0.07
    imax
    0.06
    onus
    0.06
    fuel
    0.06
    sen
    0.06
    alone
    0.06
    hed
    0.06
    uÅŁ
    0.06
    Activations Density 0.001%

    No Known Activations