© 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. 17747
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conformity or alignment with established standards or guidelines

    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
     reim
    -0.07
    ohl
    -0.06
    AXB
    -0.06
    /th
    -0.06
     Matters
    -0.06
    ks
    -0.06
    ning
    -0.06
    ntl
    -0.06
    ty
    -0.06
    eron
    -0.06
    POSITIVE LOGITS
     with
    0.10
    arser
    0.08
    erland
    0.07
    iculo
    0.07
     vỼi
    0.07
    ónico
    0.07
    	with
    0.07
    odate
    0.07
    KER
    0.07
    WithURL
    0.07
    Activations Density 0.003%

    No Known Activations