© 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. 117644
    Prev
    Next
    INDEX
    Explanations

    elements related to educational strategies and teaching methods

    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
    anno
    -0.07
    vio
    -0.07
    aat
    -0.06
    (textBox
    -0.06
    ano
    -0.06
    cil
    -0.06
    unker
    -0.06
     Passive
    -0.06
    eki
    -0.05
     approval
    -0.05
    POSITIVE LOGITS
    ajar
    0.07
    ocker
    0.07
    ìļ´
    0.07
    Expose
    0.07
     scaffold
    0.07
     scaff
    0.07
    olec
    0.06
    apur
    0.06
    ManagerInterface
    0.06
    ecer
    0.06
    Activations Density 0.003%

    No Known Activations