© 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. 15-LLAMASCOPE-RES-131K
    11. 62298
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical decompositions and representations in the context of linear algebra

    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
    Scoped
    -0.06
    STD
    -0.06
    abyrinth
    -0.06
    ometr
    -0.06
     Steven
    -0.06
    ãĤ«ãĥĨãĤ´ãĥª
    -0.06
    ç©´
    -0.06
    gorm
    -0.06
    çĥĪ
    -0.06
     washer
    -0.06
    POSITIVE LOGITS
     into
    0.07
    ersh
    0.07
    plits
    0.07
     splits
    0.07
    解
    0.07
     split
    0.07
    ixe
    0.07
    tures
    0.07
     splitted
    0.07
     splitting
    0.06
    Activations Density 0.047%

    No Known Activations