© 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 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. 119336
    Prev
    Next
    INDEX
    Explanations

    references to additional context or qualifying information

    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
    оÑĢаз
    -0.07
    ½æķ°
    -0.07
    ÑĢÑĥг
    -0.07
    pais
    -0.06
    eee
    -0.06
    zÄħd
    -0.06
    unya
    -0.06
    çĦ¡ãģĹ
    -0.06
    ocities
    -0.06
    utch
    -0.06
    POSITIVE LOGITS
    /or
    0.13
    ãĤĪãģ³
    0.11
    ä¸Ķ
    0.08
    amp
    0.08
    and
    0.08
    /of
    0.07
    /OR
    0.07
    also
    0.07
    ingga
    0.07
    iew
    0.06
    Activations Density 0.090%

    No Known Activations