© 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. 86683
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate existence, effectiveness, and the nature of conditions or relationships

    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
    orman
    -0.06
    wi
    -0.06
    557
    -0.06
    ior
    -0.06
     NavParams
    -0.06
    vable
    -0.05
    elda
    -0.05
    nton
    -0.05
    405
    -0.05
    ies
    -0.05
    POSITIVE LOGITS
    obar
    0.08
    (éĩij
    0.08
    ican
    0.08
    utzer
    0.07
    conde
    0.07
    ffect
    0.07
    FFECT
    0.07
    .scalablytyped
    0.07
    ħn
    0.07
    .setPrototypeOf
    0.07
    Activations Density 0.053%

    No Known Activations