© 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. 86646
    Prev
    Next
    INDEX
    Explanations

    variables and settings related to configuration

    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
    bu
    -0.08
    loat
    -0.07
    ACHINE
    -0.07
     pylint
    -0.07
    lasting
    -0.07
    NTSTATUS
    -0.07
    ead
    -0.07
    kate
    -0.07
     VÅ¡ech
    -0.07
    eniable
    -0.07
    POSITIVE LOGITS
    ond
    0.06
    éĢ¸
    0.06
    /dis
    0.06
    yles
    0.06
    ане
    0.06
    ÑĢÑĥÑĩ
    0.06
     gal
    0.06
     Gal
    0.06
     prod
    0.06
     hic
    0.06
    Activations Density 0.023%

    No Known Activations