© 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. 9-LLAMASCOPE-RES-131K
    11. 98635
    Prev
    Next
    INDEX
    Explanations

    phrases expressing commitment or dedication to particular actions or causes

    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
    eres
    -0.08
    ych
    -0.07
    iator
    -0.07
    -scale
    -0.07
    Ìĥ
    -0.07
    ya
    -0.07
    ãĥªãĥ¼ãĤº
    -0.06
    PCODE
    -0.06
    eur
    -0.06
    rias
    -0.06
    POSITIVE LOGITS
     PoÄįet
    0.07
    597
    0.07
    ably
    0.07
     æIJ
    0.07
    æĹ
    0.07
     baiser
    0.06
    è£ı
    0.06
     axiom
    0.06
    .radians
    0.06
    вай
    0.06
    Activations Density 0.012%

    No Known Activations