© 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 EvalsExportsAPI 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. 78412
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations that represent organizations or significant terms

    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
    Ø´ÙĪ
    -0.07
    aset
    -0.07
    æĸ
    -0.07
    泡
    -0.06
    avs
    -0.06
    oque
    -0.06
    جÙĪ
    -0.06
     Äija
    -0.06
    кап
    -0.06
    740
    -0.06
    POSITIVE LOGITS
    ehr
    0.07
    å±±å¸Ĥ
    0.06
    è¡Ľ
    0.06
     [@
    0.06
     Mich
    0.06
    *)((
    0.06
    vas
    0.06
     verdi
    0.06
    ürn
    0.06
    quir
    0.06
    Activations Density 0.001%

    No Known Activations