© 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. 15-LLAMASCOPE-RES-131K
    11. 86842
    Prev
    Next
    INDEX
    Explanations

    questions and discussions about overcoming challenges and recognizing accomplishments

    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
    -widgets
    -0.07
    arrow
    -0.06
    едак
    -0.06
    ault
    -0.06
    QualifiedName
    -0.06
    arend
    -0.06
    /uploads
    -0.05
    ay
    -0.05
    elper
    -0.05
    ----↵
    -0.05
    POSITIVE LOGITS
     corresponding
    0.12
     each
    0.11
     respectively
    0.09
    each
    0.09
     respective
    0.09
     correspond
    0.09
     Each
    0.08
    Each
    0.08
     EACH
    0.08
     ê°ģê°ģ
    0.08
    Activations Density 0.019%

    No Known Activations