© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 130105
    Prev
    Next
    INDEX
    Explanations

    technical terms and values related to programming or software compatibility

    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
     suit
    -0.07
    eses
    -0.06
    esi
    -0.06
    dess
    -0.06
     GetComponent
    -0.06
    roud
    -0.06
    Å¡t
    -0.06
     erw
    -0.06
    ioctl
    -0.05
    اسÙĬ
    -0.05
    POSITIVE LOGITS
    yd
    0.08
    HELP
    0.07
    .runtime
    0.06
    Unchecked
    0.06
    /renderer
    0.06
    /../
    0.06
    odore
    0.06
    ÑģÑĤÑĢо
    0.06
    âĻĢ
    0.06
     Aires
    0.06
    Activations Density 0.001%

    No Known Activations